#Diffusion Models

357개의 포스트

[논문리뷰] UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

Chenyu Hu이 arXiv에 게시한 'UniRecGen: Unifying Multi-View 3D Reconstruction and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #3D Generation #Multi-View Consistency #Diffusion Models #Canonical Space

2026년 4월 2일

[논문리뷰] DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

arXiv에 게시된 'DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Synthetic Motion Data #Optical Flow #Camera Control

2026년 4월 2일

[sglang] SGLang Ascend NPU에서 Ring-SP를 활용한 성능 최적화 가이드

Ascend NPU 환경에서 Ring-SP를 통해 Wan2.1 모델의 추론 성능을 약 1.88배 향상시킨 사례와 벤치마크 가이드를 소개합니다.

#SGLang #Ascend NPU #Ring-SP #Performance Optimization #Diffusion Models

2026년 4월 1일

[논문리뷰] PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models

arXiv에 게시된 'PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Human Mesh Recovery #Synthetic Data #Direct Preference Optimization #Data Generation Pipeline #3D-2D Consistency

2026년 3월 31일

[논문리뷰] DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

arXiv에 게시된 'DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #On-device AI #Image Generation #Image Editing #Unified Architecture #Task-progressive Pretraining

2026년 3월 30일

[논문리뷰] Representation Alignment for Just Image Transformers is not Easier than You Think

arXiv에 게시된 'Representation Alignment for Just Image Transformers is not Easier than You Think' 논문에 대한 자세한 리뷰입니다.

#Review #Representation Alignment #Pixel-space Diffusion #Just Image Transformers #Feature Hacking #Masked Transformer Adapter #Diffusion Models #Image Generation

2026년 3월 26일

[논문리뷰] RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

arXiv에 게시된 'RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models' 논문에 대한 자세한 리뷰입니다.

#Review #Image Restoration #Real-World Degradation #Large-Scale Image Editing Models #Diffusion Models #Data Generation #RealIR-Bench #Zero-shot Generalization #Transfer Learning

2026년 3월 26일

[논문리뷰] AVControl: Efficient Framework for Training Audio-Visual Controls

arXiv에 게시된 'AVControl: Efficient Framework for Training Audio-Visual Controls' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Visual Generation #Video Control #LoRA #Parallel Canvas Conditioning #Diffusion Models #Modularity #Efficiency

2026년 3월 26일

[논문리뷰] LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

arXiv에 게시된 'LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Novel View Synthesis (NVS)#Latent Geometry #Real-time Rendering #3D Inductive Biases #Encoder-Decoder #VGGT #Generalization #Diffusion Models

2026년 3월 25일

[논문리뷰] MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Wentao Zhang이 arXiv에 게시한 'MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding' 논문에 대한 자세한 리뷰입니다.

#Review #Document OCR #Diffusion Models #Inverse Rendering #Parallel Decoding #Block-Attention #Curriculum Learning #Vision-Language Models

2026년 3월 24일

[논문리뷰] DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

arXiv에 게시된 'DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Optical Flow Estimation #Diffusion Models #Degradation-Aware #Image Restoration #Dense Correspondence #Spatio-Temporal Attention #Hybrid Architecture

2026년 3월 24일

[논문리뷰] Repurposing Geometric Foundation Models for Multi-view Diffusion

arXiv에 게시된 'Repurposing Geometric Foundation Models for Multi-view Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Geometric Foundation Models #Multi-view Diffusion #Novel View Synthesis (NVS)#Latent Space Design #Geometric Consistency #Diffusion Models #RGB Reconstruction #3D Consistency

2026년 3월 23일

[논문리뷰] TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos

Longwen Zhang이 arXiv에 게시한 'TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #3D Texturing #Geometric Consistency #Turntable Video #Diffusion Models #Neural Rendering

2026년 3월 22일

[논문리뷰] LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

arXiv에 게시된 'LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Personalized Video Generation #Multi-Subject #Face-Attribute Alignment #Diffusion Models #Attention Mechanisms #Relational Embedding #Text-to-Video

2026년 3월 22일

[논문리뷰] SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

arXiv에 게시된 'SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction-Guided Video Editing #Diffusion Models #Semantic Anchoring #Motion Alignment #Factorized Pre-training #Zero-shot Learning #Temporal Consistency

2026년 3월 19일

[논문리뷰] EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing

arXiv에 게시된 'EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing' 논문에 대한 자세한 리뷰입니다.

#Review #Video Object Removal #Video Object Insertion #Diffusion Models #Effect Erasing #Reciprocal Learning #Deep Learning #Computer Vision

2026년 3월 19일

[논문리뷰] Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

arXiv에 게시된 'Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer' 논문에 대한 자세한 리뷰입니다.

#Review #Motion Generation #Diffusion Models #Discrete Tokens #Kinematic Control #Semantic Conditioning #Motion Tokenizer #Perception-Planning-Control

2026년 3월 19일

[논문리뷰] LoST: Level of Semantics Tokenization for 3D Shapes

arXiv에 게시된 'LoST: Level of Semantics Tokenization for 3D Shapes' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Tokenization #Semantic Salience #Autoregressive Generation #Relational Inter-Distance Alignment #Diffusion Models #Triplane

2026년 3월 18일

[논문리뷰] SegviGen: Repurposing 3D Generative Model for Part Segmentation

arXiv에 게시된 'SegviGen: Repurposing 3D Generative Model for Part Segmentation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Part Segmentation #Generative Models #Diffusion Models #Latent Space #Limited Supervision #Multi-Task Learning

2026년 3월 17일

[논문리뷰] Mixture of Style Experts for Diverse Image Stylization

Mi Zhou이 arXiv에 게시한 'Mixture of Style Experts for Diverse Image Stylization' 논문에 대한 자세한 리뷰입니다.

#Review #Image Stylization #Mixture of Experts (MoE)#Diffusion Models #Semantic-aware Stylization #Style Transfer #LoRA

2026년 3월 17일

[논문리뷰] Demystifing Video Reasoning

arXiv에 게시된 'Demystifing Video Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Reasoning #Diffusion Models #Chain-of-Steps #Emergent Behaviors #Layer Specialization #Training-Free Ensemble

2026년 3월 17일

[논문리뷰] From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

lindahua이 arXiv에 게시한 'From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #GRPO #Diffusion Models #Flow Models #Preference Alignment #Condition Enhancement #Multi-View Learning

2026년 3월 15일

[논문리뷰] WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

Zongkai Liu이 arXiv에 게시한 'WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Text-centric Image Editing #Diffusion Models #Glyph-Guided Fine-tuning #Reinforcement Learning #Multilingual Benchmark #Dataset Construction

2026년 3월 12일

[논문리뷰] DVD: Deterministic Video Depth Estimation with Generative Priors

Jing He이 arXiv에 게시한 'DVD: Deterministic Video Depth Estimation with Generative Priors' 논문에 대한 자세한 리뷰입니다.

#Review #Video Depth Estimation #Generative Priors #Deterministic Adaptation #Diffusion Models #Latent Manifold Rectification #Global Affine Coherence #Zero-shot Learning #Temporal Consistency

2026년 3월 12일

[논문리뷰] Streaming Autoregressive Video Generation via Diagonal Distillation

arXiv에 게시된 'Streaming Autoregressive Video Generation via Diagonal Distillation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Autoregressive Models #Diffusion Models #Distillation #Real-time #Streaming #Temporal Coherence #Flow Matching

2026년 3월 10일

[논문리뷰] Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

arXiv에 게시된 'Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Editing #Reinforcement Learning #Multi-view Consistency #Diffusion Models #Reward Modeling #3D Gaussian Splatting #FLUX-Kontext #VGGT

2026년 3월 10일

[논문리뷰] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

arXiv에 게시된 'TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Reinforcement Learning #Non-Differentiable Rewards #Few-Step Generation #Trajectory Distribution Matching #Surrogate Reward Learning #Text-to-Image

2026년 3월 9일

[논문리뷰] Scale Space Diffusion

Abhinav Shrivastava이 arXiv에 게시한 'Scale Space Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Scale Space Theory #Generative Models #Multi-resolution Image Generation #UNet Architecture #Image Upsampling #Non-Isotropic Noise

2026년 3월 9일

[논문리뷰] HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Bin Liu이 arXiv에 게시한 'HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Video Generation #Hierarchical Denoising #Diffusion Models #Temporal Continuity #Error Propagation #Forward-KL Regularization #Long Video Synthesis #Pipelined Parallelism

2026년 3월 9일

[논문리뷰] CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

Dan Xu이 arXiv에 게시한 'CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Mixture-of-Experts (MoE)#Condition-Aware Routing #Contextual Image Editing #Mask Repaint #Latent Mixture #Diffusion Transformer

2026년 3월 9일

[논문리뷰] WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

Mingqiang Wu이 arXiv에 게시한 'WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Diffusion Models #Inference Acceleration #Feature Caching #Heterogeneous Tokens #Curvature Prediction #Adaptive Skipping

2026년 3월 8일

[논문리뷰] WildActor: Unconstrained Identity-Preserving Video Generation

Fei Shen이 arXiv에 게시한 'WildActor: Unconstrained Identity-Preserving Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Identity Preservation #Human-Centric Video #Large-scale Dataset #Diffusion Models #Attention Mechanism #Viewpoint Consistency

2026년 3월 8일

[논문리뷰] Physical Simulator In-the-Loop Video Generation

Thabo Beeler이 arXiv에 게시한 'Physical Simulator In-the-Loop Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physical Simulation #Diffusion Models #Texture Consistency #Motion Controllability #Test-Time Optimization #4D Reconstruction

2026년 3월 8일

[논문리뷰] RealWonder: Real-Time Physical Action-Conditioned Video Generation

Hong-Xing Yu이 arXiv에 게시한 'RealWonder: Real-Time Physical Action-Conditioned Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physics Simulation #Real-Time #Action-Conditioned #3D Scene Reconstruction #Diffusion Models #Optical Flow

2026년 3월 5일

[논문리뷰] HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images

arXiv에 게시된 'HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images' 논문에 대한 자세한 리뷰입니다.

#Review #Reference-Based Inpainting #High-Fidelity Image Generation #Human-Product Images #Diffusion Models #Detail Preservation #Attention Mechanisms #Loss Functions #Dataset Construction

2026년 3월 5일

[논문리뷰] DreamWorld: Unified World Modeling in Video Generation

Shaofeng Zhang이 arXiv에 게시한 'DreamWorld: Unified World Modeling in Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #World Modeling #Diffusion Models #Multi-modal Integration #Temporal Consistency #Spatial Geometry #Semantic Consistency #Constraint Annealing

2026년 3월 5일

[논문리뷰] CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

arXiv에 게시된 'CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video' 논문에 대한 자세한 리뷰입니다.

#Review #4K 360° Video Generation #Spatio-Temporal Autoregressive #Diffusion Models #Cubemap #Context Attention #Virtual Reality #Perspective-to-Panorama

2026년 3월 4일

[논문리뷰] Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

arXiv에 게시된 'Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Instruction Guidance #Reference Guidance #Diffusion Models #MLLM #Dataset Generation #RefVIE #Curriculum Learning

2026년 3월 3일

[논문리뷰] CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance

arXiv에 게시된 'CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Classifier-Free Guidance #Control Theory #Sliding Mode Control #Text-to-Image Generation #Flow Matching #Generative AI #Robustness

2026년 3월 3일

[논문리뷰] Beyond Language Modeling: An Exploration of Multimodal Pretraining

arXiv에 게시된 'Beyond Language Modeling: An Exploration of Multimodal Pretraining' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Pretraining #Vision-Language Models #Mixture-of-Experts (MoE)#Representation Autoencoders (RAE)#World Modeling #Scaling Laws #Diffusion Models #Unified Architectures

2026년 3월 3일

[논문리뷰] NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing

Binxin Yang이 arXiv에 게시한 'NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Diffusion Models #Unpaired Learning #Temporal Consistency #Sparse Control #Dense Synthesis #Degradation Simulation #Keyframe Guidance

2026년 3월 3일

[논문리뷰] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories

arXiv에 게시된 'WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #3D Reconstruction #Camera Control #Diffusion Models #Geometric Memory #Multi-View Consistency #World Model

2026년 3월 2일

[논문리뷰] From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

arXiv에 게시된 'From Scale to Speed: Adaptive Test-Time Scaling for Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Test-Time Scaling #Chain-of-Thought #Diffusion Models #Adaptive Resource Allocation #Edit-Specific Verification #Opportunistic Stopping

2026년 3월 2일

[논문리뷰] SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

Alexandre Alahi이 arXiv에 게시한 'SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Inference Acceleration #Caching #Sensitivity Analysis #Dynamic Caching #Video Generation #Denoising

2026년 3월 1일

[논문리뷰] Mode Seeking meets Mean Seeking for Fast Long Video Generation

arXiv에 게시된 'Mode Seeking meets Mean Seeking for Fast Long Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Long Video Generation #Diffusion Models #Mode Seeking #Mean Seeking #Decoupled Diffusion Transformer #Flow Matching #Distribution Matching #Video Synthesis

2026년 3월 1일

[논문리뷰] Causal Motion Diffusion Models for Autoregressive Motion Generation

Kent Fujiwara이 arXiv에 게시한 'Causal Motion Diffusion Models for Autoregressive Motion Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Motion Generation #Diffusion Models #Autoregressive Models #Causal Modeling #Latent Space #Text-to-Motion #Human Motion Synthesis #Streaming Generation

2026년 2월 26일

[논문리뷰] Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

Jae-Gil Lee이 arXiv에 게시한 'Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Distributed Parallelism #Conditional Guidance #Adaptive Scheduling #Generative AI #Latency Reduction #Multi-GPU

2026년 2월 26일

[논문리뷰] SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

Geonho Cha이 arXiv에 게시한 'SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Model Acceleration #Feature Caching #Spectral Analysis #Generative AI #Image Generation #Video Generation #Latency Reduction

2026년 2월 25일

[논문리뷰] Image Generation with a Sphere Encoder

arXiv에 게시된 'Image Generation with a Sphere Encoder' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Sphere Encoder #Autoencoder #Latent Space #Few-Step Generation #Conditional Generation #Diffusion Models #Perceptual Loss

2026년 2월 25일

[논문리뷰] One-step Language Modeling via Continuous Denoising

Jerry Huang이 arXiv에 게시한 'One-step Language Modeling via Continuous Denoising' 논문에 대한 자세한 리뷰입니다.

#Review #Language Modeling #Continuous Denoising #Flow-based Models #Diffusion Models #One-step Generation #Few-step Sampling #Time Reparameterization #Model Distillation

2026년 2월 24일

[논문리뷰] LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency

arXiv에 게시된 'LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Completion #Zero-shot #Latent-Spatial Consistency #Foundation Models #Diffusion Models #Category-Agnostic #Generative Priors

2026년 2월 24일

[논문리뷰] Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

arXiv에 게시된 'Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Vision-Language Models #Diffusion Models #Mobile Devices #Edge Computing #Model Efficiency #Unified Architecture #Real-time Inference

2026년 2월 23일

[논문리뷰] Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control

Shengqu Cai이 arXiv에 게시한 'Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Extended Reality (XR)#Diffusion Models #Human-Computer Interaction #Hand Pose Estimation #Camera Control #World Simulation #Interactive AI

2026년 2월 22일

[논문리뷰] Unified Latents (UL): How to train your latents

arXiv에 게시된 'Unified Latents (UL): How to train your latents' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Latent Representation Learning #VAE #Image Generation #Video Generation #Bitrate Control #Training Efficiency #Diffusion Prior #Diffusion Decoder

2026년 2월 19일

[논문리뷰] SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

arXiv에 게시된 'SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse Attention #Diffusion Models #Video Generation #Hybrid Masking #Distillation Fine-Tuning #Model Acceleration #Top-k #Top-p

2026년 2월 19일

[논문리뷰] FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment

Shuai Chen이 arXiv에 게시한 'FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #World Modeling #Generalist Policies #Representation Alignment #Diffusion Models #Robotics #Fine-tuning #Egocentric Data #VLA

2026년 2월 19일

[논문리뷰] SLA2: Sparse-Linear Attention with Learnable Routing and QAT

arXiv에 게시된 'SLA2: Sparse-Linear Attention with Learnable Routing and QAT' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse-Linear Attention #Diffusion Models #Video Generation #Learnable Routing #Quantization-Aware Training #Attention Acceleration #Model Optimization

2026년 2월 18일

[논문리뷰] Optimizing Few-Step Generation with Adaptive Matching Distillation

arXiv에 게시된 'Optimizing Few-Step Generation with Adaptive Matching Distillation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Knowledge Distillation #Few-Step Generation #Adaptive Matching #Forbidden Zones #Generative Models #Sample Quality #Training Stability

2026년 2월 18일

[논문리뷰] dVoting: Fast Voting for dLLMs

arXiv에 게시된 'dVoting: Fast Voting for dLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #dLLMs #Diffusion Models #Test-Time Scaling #Voting #Reasoning #Masked Language Models #Parallel Decoding #Remasking

2026년 2월 12일

[논문리뷰] Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

arXiv에 게시된 'Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching' 논문에 대한 자세한 리뷰입니다.

#Review #Vector Sketching #Progressive Semantic Illusions #Score Distillation Sampling #Joint Optimization #Visual Anagrams #Bézier Strokes #CLIP-guided Generation #Diffusion Models

2026년 2월 12일

[논문리뷰] Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation

Yukuan Xu이 arXiv에 게시한 'Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Navigation #Beyond-the-View Navigation #Video Generation Models #Sparse Video Generation #Diffusion Models #Embodied AI #Real-world Navigation #Long-horizon Planning

2026년 2월 12일

[논문리뷰] DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

arXiv에 게시된 'DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Model #Image Generation #Image Editing #Diffusion Models #VLM-DiT Architecture #Stacked Channel Bridging #Reinforcement Learning #Lightweight Models

2026년 2월 12일

[논문리뷰] Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

arXiv에 게시된 'Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Models #Diffusion Models #Image Generation #Condition Refinement #Optimal Transport #Wasserstein Gradient Flow #Score Matching #Patch Denoising

2026년 2월 10일

[논문리뷰] WorldCompass: Reinforcement Learning for Long-Horizon World Models

arXiv에 게시된 'WorldCompass: Reinforcement Learning for Long-Horizon World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #World Models #Video Generation #Autoregressive Generation #Long-Horizon #Post-training #Diffusion Models #Reward Functions

2026년 2월 9일

[논문리뷰] Context Forcing: Consistent Autoregressive Video Generation with Long Context

arXiv에 게시된 'Context Forcing: Consistent Autoregressive Video Generation with Long Context' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Autoregressive Models #Long Context #Temporal Consistency #Diffusion Models #Context Forcing #Memory Management #Distribution Matching Distillation

2026년 2월 5일

[논문리뷰] VLS: Steering Pretrained Robot Policies via Vision-Language Models

arXiv에 게시된 'VLS: Steering Pretrained Robot Policies via Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Vision-Language Models #Policy Steering #Inference-Time Adaptation #Out-of-Distribution Generalization #Diffusion Models #Generative Policies

2026년 2월 4일

[논문리뷰] Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

arXiv에 게시된 'Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #LLM #Text-to-Image #Transformer #Semantic Routing #Feature Fusion #Dynamic Conditioning #Generative AI

2026년 2월 4일

[논문리뷰] Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

arXiv에 게시된 'Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Model Distillation #Mode Collapse #Image Generation #Diversity Preservation #Flow Matching #Few-Step Synthesis

2026년 2월 3일

[논문리뷰] 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

arXiv에 게시된 '3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Human Video Generation #3D-Aware #Implicit Motion Control #View-Adaptive #Diffusion Models #Motion Encoder #Text-Guided Camera Control

2026년 2월 3일

[논문리뷰] PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

arXiv에 게시된 'PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Video Generation #Post-Training #Optimal Transport #Reward Modeling #Annotation-free #Vision-Language Models #Diffusion Models

2026년 2월 2일

[논문리뷰] Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

Teng Hu이 arXiv에 게시한 'Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars' 논문에 대한 자세한 리뷰입니다.

#Review #Talking Avatars #Human-Object Interaction (HOI)#Text-Driven Generation #Diffusion Models #Multimodal Control #Grounded Interaction

2026년 2월 2일

[논문리뷰] Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

arXiv에 게시된 'Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Video Generation #Diffusion Models #Model Distillation #Real-Time AI #Causal Attention #ODE Distillation #Frame-level Injectivity #Teacher Forcing

2026년 2월 2일

[논문리뷰] Revisiting Diffusion Model Predictions Through Dimensionality

Chaoyang Wang이 arXiv에 게시한 'Revisiting Diffusion Model Predictions Through Dimensionality' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Prediction Target #Dimensionality #Latent Space #Pixel Space #Generative Models #Theoretical Analysis #k-Diff

2026년 2월 1일

[논문리뷰] DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning

arXiv에 게시된 'DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Character Animation #Image Animation #Spatiotemporal Learning #In-Context Learning #Diffusion Models #Motion Transfer #Generalization #Video Generation

2026년 2월 1일

[논문리뷰] DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation

Jong Chul Ye이 arXiv에 게시한 'DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoencoder #DINO #Vision Foundation Models #Image Generation #Image Reconstruction #Spherical Manifold #Diffusion Models #Flow Matching

2026년 2월 1일

[논문리뷰] iFSQ: Improving FSQ for Image Generation with 1 Line of Code

arXiv에 게시된 'iFSQ: Improving FSQ for Image Generation with 1 Line of Code' 논문에 대한 자세한 리뷰입니다.

#Review #Finite Scalar Quantization (FSQ)#Image Generation #Autoregressive Models #Diffusion Models #Quantization #Tokenization #Representation Alignment (REPA)#Latent Space

2026년 1월 26일

[논문리뷰] SkyReels-V3 Technique Report

arXiv에 게시된 'SkyReels-V3 Technique Report' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multimodal AI #Diffusion Models #Transformer Architecture #Reference-guided Generation #Video-to-Video #Audio-driven Animation #Temporal Consistency

2026년 1월 26일

[논문리뷰] VideoMaMa: Mask-Guided Video Matting via Generative Prior

arXiv에 게시된 'VideoMaMa: Mask-Guided Video Matting via Generative Prior' 논문에 대한 자세한 리뷰입니다.

#Review #Video Matting #Diffusion Models #Generative Priors #Mask-Guided #Pseudo-labeling #Large-scale Dataset #Zero-shot Generalization

2026년 1월 22일

[논문리뷰] Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

arXiv에 게시된 'Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Diffusion Models #Representation Autoencoder #Latent Space #Large-Scale Models #Unified Models #Noise Scheduling

2026년 1월 22일

[논문리뷰] Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

arXiv에 게시된 'Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Models #Visuomotor Control #Robot Policy #Fine-tuning #Diffusion Models #World Models #Model-based Planning #Imitation Learning

2026년 1월 22일

[논문리뷰] OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

arXiv에 게시된 'OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer' 논문에 대한 자세한 리뷰입니다.

#Review #Video Transfer #Diffusion Models #Spatio-temporal Learning #Multimodal Alignment #Appearance Consistency #Temporal Control #Video Generation

2026년 1월 20일

[논문리뷰] CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation

Hengshuang이 arXiv에 게시한 'CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-subject Animation #Pose-driven Animation #Diffusion Models #Spatial Misalignment #Unbind-Rebind Paradigm #Character Animation #Video Generation

2026년 1월 19일

[논문리뷰] VIBE: Visual Instruction Based Editor

Bulat Suleimanov이 arXiv에 게시한 'VIBE: Visual Instruction Based Editor' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction-Based Image Editing #Diffusion Models #Vision-Language Models (VLM)#Model Efficiency #Multi-stage Training #Preference Alignment #Source Consistency

2026년 1월 15일

[논문리뷰] Transition Matching Distillation for Fast Video Generation

arXiv에 게시된 'Transition Matching Distillation for Fast Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Model Distillation #Few-Step Sampling #Transition Matching #Flow Matching #DMD2 #Efficiency

2026년 1월 15일

[논문리뷰] Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

arXiv에 게시된 'Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image #Diffusion Models #LLM Encoders #Reasoning-Aware AI #Reinforcement Learning #Dual-GRPO #Prompt Rewriting

2026년 1월 15일

[논문리뷰] CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

arXiv에 게시된 'CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Video Models #Visual Reasoning #Chain-of-Frame (CoF)#Progressive Refinement #Diffusion Models #CoF-Evol-Instruct

2026년 1월 15일

[논문리뷰] Alterbute: Editing Intrinsic Attributes of Objects in Images

arXiv에 게시된 'Alterbute: Editing Intrinsic Attributes of Objects in Images' 논문에 대한 자세한 리뷰입니다.

#Review #Intrinsic Attributes #Object Editing #Diffusion Models #Identity Preservation #Visual Named Entities #Text-to-Image #VLM

2026년 1월 15일

[논문리뷰] Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering

Ayush Tewari이 arXiv에 게시한 'Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #3D Reconstruction #3D Gaussian Splatting #Camera-Controlled #Sparse Keyframes #Real-time #Computational Efficiency

2026년 1월 14일

[논문리뷰] Motion Attribution for Video Generation

arXiv에 게시된 'Motion Attribution for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Motion Attribution #Video Generation #Diffusion Models #Gradient-based Attribution #Temporal Dynamics #Motion Masking #Fine-tuning #Data Curation

2026년 1월 13일

[논문리뷰] End-to-End Video Character Replacement without Structural Guidance

arXiv에 게시된 'End-to-End Video Character Replacement without Structural Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Video Character Replacement #Diffusion Models #In-Context Learning #Reinforcement Learning #Structural Guidance #Video Editing #Data Generation Pipeline

2026년 1월 13일

[논문리뷰] Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

Arjan Chakravarthy이 arXiv에 게시한 'Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #World Models #Physics-Conditioned Goals #Causal Planning #Force Vectors #Zero-Shot Generalization #Diffusion Models #Robotics Planning

2026년 1월 11일

[논문리뷰] VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Ying Shan이 arXiv에 게시한 'VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control' 논문에 대한 자세한 리뷰입니다.

#Review #Video World Model #4D Geometric Control #Gaussian Trajectories #Video Generation #Diffusion Models #Camera Control #Object Motion Control #Data Engine

2026년 1월 8일

[논문리뷰] RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

Mingda Jia이 arXiv에 게시한 'RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Manipulation #Data Augmentation #Video Generation #Diffusion Models #Multi-View #Visual Identity Prompting #Action-Guided Segmentation #Visuomotor Policy

2026년 1월 8일

[논문리뷰] Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

Yu Xu이 arXiv에 게시한 'Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #In-Context Image Generation #Image Editing #Multimodal Models #Chain-of-Thought #Structured Reasoning #Reinforcement Learning #Alignment #Diffusion Models

2026년 1월 8일

[논문리뷰] Memorization in 3D Shape Generation: An Empirical Study

arXiv에 게시된 'Memorization in 3D Shape Generation: An Empirical Study' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Generation #Memorization #Generative Models #Diffusion Models #Evaluation Framework #Generalization #Data Augmentation

2026년 1월 8일

[논문리뷰] DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs

Jing Ma이 arXiv에 게시한 'DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Chain-of-Thought #Diffusion Models #Large Language Models #Reasoning #Error Correction #Preference Optimization #Denoising

2026년 1월 8일

[논문리뷰] DreamStyle: A Unified Framework for Video Stylization

arXiv에 게시된 'DreamStyle: A Unified Framework for Video Stylization' 논문에 대한 자세한 리뷰입니다.

#Review #Video Stylization #Unified Framework #Diffusion Models #LoRA #Data Curation #Multi-modal Input #Image-to-Video

2026년 1월 6일

[논문리뷰] Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Shuo Yang이 arXiv에 게시한 'Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Text-Guided Image Editing #Object-Level Transformation #Geometric Transformation #Diffusion Models #GRPO #Scene Editing #Spatially Grounded Rewards

2026년 1월 5일

[논문리뷰] M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models

Jun-Cheng Chen이 arXiv에 게시한 'M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Concept Erasure #Multimodal Evaluation #Adversarial Attacks #Robustness #Textual Inversion #Latent Inversion #Cross-Attention

2026년 1월 5일

[논문리뷰] GARDO: Reinforcing Diffusion Models without Reward Hacking

Zhiyong Wang이 arXiv에 게시한 'GARDO: Reinforcing Diffusion Models without Reward Hacking' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Reinforcement Learning #Reward Hacking #KL Regularization #Adaptive Regularization #Diversity Optimization #Text-to-Image Generation

2026년 1월 5일

[논문리뷰] Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

arXiv에 게시된 'Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #MLLMs #Video Understanding #Hallucinations #Counterfactual Generation #Diffusion Models #Reinforcement Learning #QA Dataset #DNA-Train

2026년 1월 4일

[논문리뷰] Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Sung Ju Hwang이 arXiv에 게시한 'Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation' 논문에 대한 자세한 리뷰입니다.

#Review #Avatar Generation #Real-Time Interaction #Diffusion Models #Preference Optimization #Causal Inference #Multimodal Input #Head Avatar

2026년 1월 4일

[논문리뷰] On the Role of Discreteness in Diffusion LLMs

arXiv에 게시된 'On the Role of Discreteness in Diffusion LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Language Models #Discrete Text #Continuous Diffusion #Text Generation #Data Augmentation #Parallel Decoding #Structural Dependency

2026년 1월 1일

[논문리뷰] DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

Siyuan Huang이 arXiv에 게시한 'DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reasoning #Diffusion Models #Image-to-Image Generation #Vision-centric AI #Generative AI #Spatial Planning #Constraint Satisfaction

2026년 1월 1일

[논문리뷰] Pretraining Frame Preservation in Autoregressive Video Memory Compression

Beijia Lu이 arXiv에 게시한 'Pretraining Frame Preservation in Autoregressive Video Memory Compression' 논문에 대한 자세한 리뷰입니다.

#Review #Video Compression #Autoregressive Models #Memory Compression #Frame Preservation #Pretraining #Video Generation #Diffusion Models #Long-Range Consistency

2025년 12월 31일

[논문리뷰] Guiding a Diffusion Transformer with the Internal Dynamics of Itself

arXiv에 게시된 'Guiding a Diffusion Transformer with the Internal Dynamics of Itself' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Transformer #Generative AI #Image Generation #Guidance Strategy #Internal Guidance #Auxiliary Loss #Classifier-Free Guidance

2025년 12월 31일

[논문리뷰] GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction

Yu-Lun Liu이 arXiv에 게시한 'GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #Sparse-View #Diffusion Models #Outpainting #Gaussian Splatting #Geometry-aware #Novel View Synthesis

2025년 12월 31일

[논문리뷰] UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

Kaiyi Zhang이 arXiv에 게시한 'UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Generation #Diffusion Models #Geometric Refinement #Data Curation #Watertight Mesh #Voxel-based #Scalability #High-Fidelity

2025년 12월 30일

[논문리뷰] DreamOmni3: Scribble-based Editing and Generation

arXiv에 게시된 'DreamOmni3: Scribble-based Editing and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Image Generation #Scribble-based Control #Multimodal AI #Diffusion Models #Data Synthesis #Human-Computer Interaction #Instruction-based Editing

2025년 12월 30일

[논문리뷰] Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Po-Fan Yu이 arXiv에 게시한 'Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Video Super-Resolution #Diffusion Models #Low-Latency #Streamable #Auto-Regressive #Model Distillation #Temporal Consistency #Perceptual Quality

2025년 12월 29일

[논문리뷰] GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

arXiv에 게시된 'GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Text Encoder #Diffusion Models #Text Embedding #Evaluation Benchmark #MLLM Fine-tuning #Layer-wise Weighting #Text-to-Image Generation #Text-to-Video Generation

2025년 12월 29일

[논문리뷰] Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

arXiv에 게시된 'Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Vision-Language Models #Vision-Language-Action Models #Robotics #Multimodal AI #Action Planning #Long-Horizon Planning #Bidirectional Attention

2025년 12월 29일

[논문리뷰] ProEdit: Inversion-based Editing From Prompts Done Right

Kun-Yu Lin이 arXiv에 게시한 'ProEdit: Inversion-based Editing From Prompts Done Right' 논문에 대한 자세한 리뷰입니다.

#Review #Inversion-based Editing #Text-to-Image Editing #Text-to-Video Editing #Diffusion Models #Flow-based Models #Attention Mechanism #Latent Space Manipulation #Plug-and-Play

2025년 12월 28일

[논문리뷰] InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion

arXiv에 게시된 'InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion' 논문에 대한 자세한 리뷰입니다.

#Review #Video Object Insertion (VOI)#4D Scene Geometry #Diffusion Models #Mask Generation #Temporal Consistency #Occlusion Handling #Illumination Synthesis #ROSE++ Dataset

2025년 12월 28일

[논문리뷰] Spatia: Video Generation with Updatable Spatial Memory

arXiv에 게시된 'Spatia: Video Generation with Updatable Spatial Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Spatial Memory #3D Scene Point Cloud #Spatial Consistency #Camera Control #Interactive Editing #Diffusion Models #Visual SLAM

2025년 12월 25일

[논문리뷰] How Much 3D Do Video Foundation Models Encode?

arXiv에 게시된 'How Much 3D Do Video Foundation Models Encode?' 논문에 대한 자세한 리뷰입니다.

#Review #Video Foundation Models #3D Understanding #3D Reconstruction #Model Agnostic #Feature Probing #Diffusion Models #Temporal Reasoning

2025년 12월 25일

[논문리뷰] TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

arXiv에 게시된 'TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Acceleration #Quantization #Attention #Step Distillation #Performance Optimization #RTX 5090

2025년 12월 24일

[논문리뷰] HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

arXiv에 게시된 'HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming' 논문에 대한 자세한 리뷰입니다.

#Review #High-Resolution Video Generation #Diffusion Models #Autoregressive #Efficiency #Caching #Attention Mechanisms #Video Streaming #Temporal Consistency

2025년 12월 24일

[논문리뷰] SemanticGen: Video Generation in Semantic Space

arXiv에 게시된 'SemanticGen: Video Generation in Semantic Space' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Semantic Space #Diffusion Models #VAE Latents #Long Video Generation #Semantic Encoders #Generative AI

2025년 12월 23일

[논문리뷰] StoryMem: Multi-shot Long Video Storytelling with Memory

arXiv에 게시된 'StoryMem: Multi-shot Long Video Storytelling with Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Video Storytelling #Multi-shot Video Generation #Memory Mechanism #Diffusion Models #Cross-shot Consistency #Latent Video Diffusion #ROPE Shift #Keyframe Selection

2025년 12월 22일

[논문리뷰] Region-Constraint In-Context Generation for Instructional Video Editing

arXiv에 게시된 'Region-Constraint In-Context Generation for Instructional Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #In-Context Learning #Diffusion Models #Region-Constraint #Instruction-based Editing #Latent Space Regularization #Attention Space Regularization #Large-scale Dataset

2025년 12월 22일

[논문리뷰] MatSpray: Fusing 2D Material World Knowledge on 3D Geometry

arXiv에 게시된 'MatSpray: Fusing 2D Material World Knowledge on 3D Geometry' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #Material Estimation #Diffusion Models #Gaussian Splatting #Inverse Rendering #PBR #Relighting #Neural Merger

2025년 12월 22일

[논문리뷰] LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

arXiv에 게시된 'LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding' 논문에 대한 자세한 리뷰입니다.

#Review #dLLM #Parallel Decoding #Lookahead #Inference Acceleration #Token Filling Order #Branch Parallelism #Diffusion Models

2025년 12월 22일

[논문리뷰] Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation

arXiv에 게시된 'Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Camera Control #Homography #Diffusion Models #Data Augmentation #Novel View Synthesis #Pose Fidelity

2025년 12월 22일

[논문리뷰] RadarGen: Automotive Radar Point Cloud Generation from Cameras

Or Litany이 arXiv에 게시한 'RadarGen: Automotive Radar Point Cloud Generation from Cameras' 논문에 대한 자세한 리뷰입니다.

#Review #Radar Point Cloud Generation #Diffusion Models #Camera-to-Radar #BEV Representation #Autonomous Driving #Multi-modal Generative Models #Scene Editing

2025년 12월 21일

[논문리뷰] The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text

arXiv에 게시된 'The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Video Generation #Multimodal Control #Trajectory Guidance #Reference Images #Promptable Events #Cross-Attention #Diffusion Models

2025년 12월 18일

[논문리뷰] StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

arXiv에 게시된 'StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors' 논문에 대한 자세한 리뷰입니다.

#Review #Monocular-to-Stereo Conversion #Video Generation #Diffusion Models #Feed-Forward Architecture #Domain Switcher #Cycle Consistency #Unified Dataset #Depth Ambiguity

2025년 12월 18일

[논문리뷰] RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Yuqi Liu이 arXiv에 게시한 'RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Vision-Language Models #Diffusion Models #Region-aligned Guidance #Reinforcement Learning #Instruction-Visual Complexity #Attention Mechanism

2025년 12월 18일

[논문리뷰] Generative Refocusing: Flexible Defocus Control from a Single Image

Yu-Lun Liu이 arXiv에 게시한 'Generative Refocusing: Flexible Defocus Control from a Single Image' 논문에 대한 자세한 리뷰입니다.

#Review #Generative AI #Image Refocusing #Defocus Deblurring #Bokeh Synthesis #Depth of Field Control #Semi-Supervised Learning #Diffusion Models #Aperture Shape Control

2025년 12월 18일

[논문리뷰] FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering

Hendrik P. A. Lensch이 arXiv에 게시한 'FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering' 논문에 대한 자세한 리뷰입니다.

#Review #Neural Rendering #Diffusion Models #G-Buffer #Autoregressive Generation #Temporal Consistency #ControlNet #ControlLoRA #Interactive Applications

2025년 12월 18일

[논문리뷰] FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

arXiv에 게시된 'FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction' 논문에 대한 자세한 리뷰입니다.

#Review #Portrait Animation #Diffusion Models #Inference Acceleration #Identity Preservation #Video Generation #Latent Prediction #Sliding Window

2025년 12월 18일

[논문리뷰] Robust and Calibrated Detection of Authentic Multimedia Content

arXiv에 게시된 'Robust and Calibrated Detection of Authentic Multimedia Content' 논문에 대한 자세한 리뷰입니다.

#Review #Deepfake Detection #Content Authenticity #Generative Models #Adversarial Robustness #Image Inversion #Plausible Deniability #Diffusion Models #Multimedia Forensics

2025년 12월 17일

[논문리뷰] Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Xiao Xu이 arXiv에 게시한 'Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Layer Decomposition #RGBA Layers #Variational Autoencoder (VAE)#Multi-stage Training #Photoshop Documents (PSD)#Inherent Editability

2025년 12월 17일

[논문리뷰] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

arXiv에 게시된 'DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Vision Language Models #Autoregressive Models #Diffusion Finetuning #Block Diffusion #Multimodal AI #KV Cache

2025년 12월 17일

[논문리뷰] ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement

Zhaohe Liao이 arXiv에 게시한 'ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement' 논문에 대한 자세한 리뷰입니다.

#Review #Table Visualization #Infographic Generation #Multi-modal Large Language Models (MLLMs)#Diffusion Models #Self-Correction #Reinforcement Learning #Graphic Design #Data-to-Visual Mapping

2025년 12월 16일

[논문리뷰] Towards Interactive Intelligence for Digital Humans

Yifei Huang이 arXiv에 게시한 'Towards Interactive Intelligence for Digital Humans' 논문에 대한 자세한 리뷰입니다.

#Review #Digital Human #Interactive Intelligence #Multimodal Interaction #LLM Agent #Real-time Animation #Persona Fidelity #Diffusion Models

2025년 12월 15일

[논문리뷰] Image Diffusion Preview with Consistency Solver

arXiv에 게시된 'Image Diffusion Preview with Consistency Solver' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Efficient Sampling #Reinforcement Learning #ODE Solvers #Image Generation #Consistency #Diffusion Preview

2025년 12월 15일

[논문리뷰] V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties

arXiv에 게시된 'V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Intrinsic Decomposition #Video Generation #Diffusion Models #Keyframe Editing #Inverse Rendering #Temporal Consistency #Physically Based Rendering

2025년 12월 14일

[논문리뷰] Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation

Qifeng Chen이 arXiv에 게시한 'Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Motion Tracking #Diffusion Models #Structure Preservation #SAM2 #Feature Distillation #Local Gram Flow

2025년 12월 14일

[논문리뷰] PersonaLive! Expressive Portrait Image Animation for Live Streaming

Jue Wang이 arXiv에 게시한 'PersonaLive! Expressive Portrait Image Animation for Live Streaming' 논문에 대한 자세한 리뷰입니다.

#Review #Live Streaming #Portrait Animation #Diffusion Models #Real-time AI #Appearance Distillation #Micro-chunk Streaming #Motion Control #Low Latency

2025년 12월 14일

[논문리뷰] Exploring MLLM-Diffusion Information Transfer with MetaCanvas

arXiv에 게시된 'Exploring MLLM-Diffusion Information Transfer with MetaCanvas' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models (MLLMs)#Diffusion Models #Image Generation #Video Generation #Image Editing #Video Editing #Latent Space Planning #Canvas Tokens #Information Transfer

2025년 12월 14일

[논문리뷰] ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning

Yujin Han이 arXiv에 게시한 'ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Reasoning #Unified Models #Self-Reflective Learning #Vision-Language Models (VLMs)#Diffusion Models #RVE-Bench

2025년 12월 11일

[논문리뷰] H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos

Mike Zheng Shou이 arXiv에 게시한 'H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos' 논문에 대한 자세한 리뷰입니다.

#Review #Video-to-Video Translation #Robot Learning #Human-Robot Transfer #Diffusion Models #Unpaired Data Learning #Pose-Guided Generation #Embodiment Gap Bridging

2025년 12월 11일

[논문리뷰] VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory

arXiv에 게시된 'VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Video Generation #Diffusion Models #Hybrid Memory #State-Space Models (SSM)#Long Video Synthesis #Temporal Consistency #Interactive AI

2025년 12월 10일

[논문리뷰] StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Guixun Luo이 arXiv에 게시한 'StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Monocular-to-Stereo #Video Generation #Diffusion Models #Geometry-Aware #XR #IPD-aligned Dataset #Novel View Synthesis

2025년 12월 10일

[논문리뷰] Composing Concepts from Images and Videos via Concept-prompt Binding

arXiv에 게시된 'Composing Concepts from Images and Videos via Concept-prompt Binding' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Concept Composition #Diffusion Models #Text-to-Video Generation #Concept Binding #Hierarchical Binder #Diversify-and-Absorb Mechanism #Temporal Disentanglement #One-shot Learning

2025년 12월 10일

[논문리뷰] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

arXiv에 게시된 'Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Motion Control #Latent Trajectory Guidance #Image-to-Video #Diffusion Models #Neural Networks #MoveBench

2025년 12월 9일

[논문리뷰] TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Weirui Ye이 arXiv에 게시한 'TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Diffusion Models #Generative Models #Tree Search #Sample Efficiency #Credit Assignment #GRPO #Visual Generative Models

2025년 12월 9일

[논문리뷰] Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

arXiv에 게시된 'Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality' 논문에 대한 자세한 리뷰입니다.

#Review #Face Swapping #Video Editing #Diffusion Models #Reference-guided Generation #Temporal Consistency #Keyframe Conditioning #Cinematic Quality #Dataset Construction

2025년 12월 9일

[논문리뷰] OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

arXiv에 게시된 'OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Shot Video Generation #Adaptive Memory #Long-Range Context #Frame Selection #Diffusion Models #Image-to-Video #Autoregressive Generation #Narrative Coherence

2025년 12월 9일

[논문리뷰] MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment

arXiv에 게시된 'MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Robotic Manipulation #Hierarchical Framework #Reinforcement Learning #Diffusion Models #World Models #Cognitive Science #Physical Alignment

2025년 12월 9일

[논문리뷰] UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

arXiv에 게시된 'UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multi-modal Learning #Multi-task Learning #Zero-shot Generalization #Diffusion Models #World Models #Video Understanding

2025년 12월 8일

[논문리뷰] Unified Video Editing with Temporal Reasoner

arXiv에 게시된 'Unified Video Editing with Temporal Reasoner' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Diffusion Models #Temporal Reasoning #Chain-of-Thought #In-Context Learning #ROPE #Multi-instance Editing

2025년 12월 8일

[논문리뷰] Scaling Zero-Shot Reference-to-Video Generation

arXiv에 게시된 'Scaling Zero-Shot Reference-to-Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Reference-to-Video Generation #Zero-Shot Learning #Diffusion Models #Masked Training #Video-Text Pairs #Identity Preservation #Scalability #Attention Mechanism

2025년 12월 8일

[논문리뷰] ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation

Taojun Ding이 arXiv에 게시한 'ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Camera Control #Novel Trajectory #3D Gaussian Splatting (3DGS)#LiDAR-Free #Diffusion Models #Autonomous Driving #Scene Synthesis

2025년 12월 8일

[논문리뷰] EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

arXiv에 게시된 'EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Egocentric Video Editing #Real-Time Streaming #Augmented Reality #Video Generation #Dataset #Benchmark #Diffusion Models #Distillation

2025년 12월 8일

[논문리뷰] Distribution Matching Variational AutoEncoder

arXiv에 게시된 'Distribution Matching Variational AutoEncoder' 논문에 대한 자세한 리뷰입니다.

#Review #Variational Autoencoder (VAE)#Distribution Matching #Diffusion Models #Latent Space #Self-supervised Learning (SSL) Features #Generative Models #ImageNet #Tokenizer

2025년 12월 8일

[논문리뷰] TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

arXiv에 게시된 'TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Models #One-step Generation #Self-Adversarial Learning #Flow Matching #Large Language Models #Text-to-Image #Efficient Inference #Diffusion Models

2025년 12월 7일

[논문리뷰] RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards

Zilong Huang이 arXiv에 게시한 'RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Photorealism #Reinforcement Learning #Diffusion Models #Adversarial Learning #Detector-Guided Rewards #LLM Prompt Optimization #Image Quality Assessment

2025년 12월 7일

[논문리뷰] NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

Vitor Guizilini이 arXiv에 게시한 'NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Phase Preservation #Frequency Domain #Structure-Aligned Generation #Image-to-Image Translation #Sim-to-Real #Generative AI

2025년 12월 4일

[논문리뷰] Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Shifeng Zhang이 arXiv에 게시한 'Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Driven Avatar Generation #Real-time Streaming #Diffusion Models #Infinite Length #Pipeline Parallelism #Temporal Consistency #Model Distillation

2025년 12월 4일

[논문리뷰] LATTICE: Democratize High-Fidelity 3D Generation at Scale

Qingxiang Lin이 arXiv에 게시한 'LATTICE: Democratize High-Fidelity 3D Generation at Scale' 논문에 대한 자세한 리뷰입니다.

#Review #3D Generation #High-Fidelity #Latent Representation #Voxel Grid #Diffusion Models #Transformer #Scalable AI #Asset Creation

2025년 12월 4일

[논문리뷰] Generative Neural Video Compression via Video Diffusion Prior

arXiv에 게시된 'Generative Neural Video Compression via Video Diffusion Prior' 논문에 대한 자세한 리뷰입니다.

#Review #Neural Video Compression #Diffusion Models #Generative Models #Video Compression #Temporal Coherence #Perceptual Quality #Flow Matching #Video Diffusion Transformer (VideoDiT)

2025년 12월 4일

[논문리뷰] BulletTime: Decoupled Control of Time and Camera Pose for Video Generation

Jan Ackermann이 arXiv에 게시한 'BulletTime: Decoupled Control of Time and Camera Pose for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #4D Control #Camera Pose Control #Time Control #Positional Encoding #Adaptive Normalization #Synthetic Dataset

2025년 12월 4일

[논문리뷰] RELIC: Interactive Video World Model with Long-Horizon Memory

Chongjian Ge이 arXiv에 게시한 'RELIC: Interactive Video World Model with Long-Horizon Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Interactive World Model #Video Generation #Long-Horizon Memory #Real-Time Streaming #Diffusion Models #Autoregressive Models #Spatial Consistency #Unreal Engine

2025년 12월 3일

[논문리뷰] CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

Yi Yao이 arXiv에 게시한 'CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-step Image Generation #Recipe Illustration #Diffusion Models #Consistent Generation #Regional Control #Positional Encoding #Ingredient Consistency #Procedural Content Generation

2025년 12월 3일

[논문리뷰] YingVideo-MV: Music-Driven Multi-Stage Video Generation

Chaofan Ding이 arXiv에 게시한 'YingVideo-MV: Music-Driven Multi-Stage Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Music-Driven Video Generation #Diffusion Models #Multi-Stage Framework #Camera Control #Lip-Sync #Temporal Coherence #Video Diffusion Transformer

2025년 12월 2일

[논문리뷰] Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation

Yu Ning이 arXiv에 게시한 'Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Spatial Reasoning #Visuospatial Intelligence #Diffusion Models #Context-Guided Generation #Scene Navigation #Object Grounding #Out-of-Domain Generalization

2025년 12월 2일

[논문리뷰] MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

arXiv에 게시된 'MultiShotMaster: A Controllable Multi-Shot Video Generation Framework' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Shot Video Generation #Controllable Video Generation #Diffusion Models #RoPE #Spatiotemporal Consistency #Reference Injection #Data Curation Framework

2025년 12월 2일

[논문리뷰] Glance: Accelerating Diffusion Models with 1 Sample

Linjie Li이 arXiv에 게시한 'Glance: Accelerating Diffusion Models with 1 Sample' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Acceleration #Distillation #LoRA #Few-shot Learning #Phase-aware #Image Generation #Computational Efficiency

2025년 12월 2일

[논문리뷰] DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation

Zixin Zhang이 arXiv에 게시한 'DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Video Generation #Camera Control #Depth Estimation #Dual-Branch Architecture #Geometric Awareness #Semantic Alignment #Multi-modal Fusion

2025년 12월 2일

[논문리뷰] Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

arXiv에 게시된 'Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Audio-Video Multimodal #Joint Denoising #Diffusion Models #Transformer Architecture #World Models #Physical Commonsense #Multimodal Training

2025년 12월 2일

[논문리뷰] C^2DLM: Causal Concept-Guided Diffusion Large Language Models

Xinpeng Dong이 arXiv에 게시한 'C^2DLM: Causal Concept-Guided Diffusion Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Large Language Models #Causality #Attention Mechanism #Reasoning #Natural Language Generation #Supervised Fine-Tuning #Concept-Guided

2025년 12월 2일

[논문리뷰] WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing

Wendong Bu이 arXiv에 게시한 'WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Benchmarking #Cognitive AI #Creativity #Multimodal AI #Knowledge-based Reasoning #Diffusion Models #MLLMs

2025년 12월 1일

[논문리뷰] Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

Wenhua Wu이 arXiv에 게시한 'Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Cultural Consistency #Multilingual AI #Neuron Activation #Cultural Probing #Fine-Tuning #Diffusion Models

2025년 12월 1일

[논문리뷰] What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

arXiv에 게시된 'What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Newtonian Dynamics #Physics-aware AI #Post-Training #Verifiable Rewards #Optical Flow #Mass Estimation

2025년 12월 1일

[논문리뷰] The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

arXiv에 게시된 'The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Image Editing #Diffusion Models #Consistency Correction #Attention Mechanism #Reference-Guided #Agent Framework #Data Curation

2025년 12월 1일

[논문리뷰] Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Ying-Cong Chen이 arXiv에 게시한 'Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model' 논문에 대한 자세한 리뷰입니다.

#Review #Geometric Dense Prediction #Depth Estimation #Surface Normal Prediction #Diffusion Models #Rectified Flow #Generative Priors #Deterministic Inference #Two-Stage Framework

2025년 12월 1일

[논문리뷰] Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

arXiv에 게시된 'Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Image Generation #Distillation #Reinforcement Learning #Few-Step Sampling #Timestep-Aware #Pixel-GAN #Model Efficiency

2025년 12월 1일

[논문리뷰] Vision Bridge Transformer at Scale

Xinchao Wang이 arXiv에 게시한 'Vision Bridge Transformer at Scale' 논문에 대한 자세한 리뷰입니다.

#Review #Vision Transformer #Bridge Models #Conditional Generation #Image Editing #Video Translation #Velocity Matching #Diffusion Models #Scalability

2025년 11월 30일

[논문리뷰] Test-time scaling of diffusions with flow maps

Sanja Fidler이 arXiv에 게시한 'Test-time scaling of diffusions with flow maps' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Flow Maps #Test-time Adaptation #Reward Guidance #Generative Models #SMC #Vision-Language Models

2025년 11월 30일

[논문리뷰] OmniRefiner: Reinforcement-Guided Local Diffusion Refinement

Yiren Song이 arXiv에 게시한 'OmniRefiner: Reinforcement-Guided Local Diffusion Refinement' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Image Refinement #Reinforcement Learning #Fine-Grained Editing #Reference-Guided Generation #Latent Diffusion #Visual Fidelity #Detail Restoration

2025년 11월 30일

[논문리뷰] Layer-Aware Video Composition via Split-then-Merge

Wen-Sheng Chu이 arXiv에 게시한 'Layer-Aware Video Composition via Split-then-Merge' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Video Composition #Diffusion Models #Layer-Aware Generation #Self-Composition #Affordance Learning #Video Editing #Data Augmentation

2025년 11월 30일

[논문리뷰] Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration

arXiv에 게시된 'Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration' 논문에 대한 자세한 리뷰입니다.

#Review #3D Geometry Synthesis #Diffusion Models #Acceleration #Caching #Training-free #Flow Matching #Voxel Stabilization #Computational Efficiency

2025년 11월 30일

[논문리뷰] DiP: Taming Diffusion Models in Pixel Space

Xu Chen이 arXiv에 게시한 'DiP: Taming Diffusion Models in Pixel Space' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Pixel Space #Latent Diffusion Models (LDMs)#Diffusion Transformer (DiT)#Patch Detailer Head #Global-Local Modeling #Computational Efficiency #ImageNet

2025년 11월 30일

[논문리뷰] Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

arXiv에 게시된 'Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Model Distillation #Classifier-Free Guidance (CFG)#Distribution Matching #Text-to-Image Generation #Few-step Generation #Regularization #Score-based Models

2025년 11월 30일

[논문리뷰] Captain Safari: A World Engine

Yitong Li이 arXiv에 게시한 'Captain Safari: A World Engine' 논문에 대한 자세한 리뷰입니다.

#Review #World Engine #3D Consistent Video Generation #Pose-conditioned Memory #Camera Control #FPV Video Synthesis #Diffusion Models #Drone Video Dataset

2025년 11월 30일

[논문리뷰] AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement

Yicheng Ji이 arXiv에 게시한 'AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Person Video Generation #Audio-Driven Animation #Diffusion Models #Interactivity Refinement #Identity-Aware Attention #Scalability #Data Efficiency

2025년 11월 30일

[논문리뷰] Video Generation Models Are Good Latent Reward Models

arXiv에 게시된 'Video Generation Models Are Good Latent Reward Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Reward Feedback Learning #Latent Space #Diffusion Models #Human Preferences #Motion Quality #Process-aware

2025년 11월 27일

[논문리뷰] MIRA: Multimodal Iterative Reasoning Agent for Image Editing

Jiebo Luo이 arXiv에 게시한 'MIRA: Multimodal Iterative Reasoning Agent for Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Multimodal AI #Iterative Reasoning #Agentic AI #Reinforcement Learning #Diffusion Models #Vision-Language Models #Instruction Following

2025년 11월 27일

[논문리뷰] Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Kfir Aberman이 arXiv에 게시한 'Canvas-to-Image: Compositional Image Generation with Multimodal Controls' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Diffusion Models #Compositional Control #Multimodal Control #Unified Canvas #Multi-Task Learning #Personalization

2025년 11월 27일

[논문리뷰] Terminal Velocity Matching

Jiaming Song이 arXiv에 게시한 'Terminal Velocity Matching' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Models #Flow Matching #Diffusion Models #One-Step Generation #Few-Step Generation #Wasserstein Distance #Transformer Architecture #Lipschitz Continuity

2025년 11월 26일

[논문리뷰] Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs

Xin Yang이 arXiv에 게시한 'Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Timestep Distillation #Consistency Models #Latent Space #Image-Free Training #Efficiency Optimization #Trajectory Sampling #Continuous-Time Learning

2025년 11월 26일

[논문리뷰] Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

arXiv에 게시된 'Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Visual Generation #Cross-Modal Synchronization #Diffusion Models #Cross-Task Synergy #Classifier-Free Guidance #Multimodal AI #Generative AI

2025년 11월 26일

[논문리뷰] Block Cascading: Training Free Acceleration of Block-Causal Video Models

arXiv에 게시된 'Block Cascading: Training Free Acceleration of Block-Causal Video Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Block-Causal Models #Inference Acceleration #Multi-GPU Parallelism #Training-Free #KV Caching #Interactive AI

2025년 11월 26일

[논문리뷰] iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

arXiv에 게시된 'iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Video Models #Diffusion Models #Many-to-many #Unified Framework #Temporal Consistency #Image Editing #Positional Embedding

2025년 11월 25일

[논문리뷰] PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding

Hongzhi Zhang이 arXiv에 게시한 'PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physics Simulation #Controllable AI #Part-Aware #Semantic Grounding #Material Properties #Image-to-Video #Diffusion Models

2025년 11월 25일

[논문리뷰] MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts

arXiv에 게시된 'MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts' 논문에 대한 자세한 리뷰입니다.

#Review #3D City Generation #Natural Language Processing #Aesthetic Adaptation #Controllable Assets #Layout Generation #Interactive Editing #Diffusion Models #Multimodal Dataset

2025년 11월 25일

[논문리뷰] DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection

Mike Zheng Shou이 arXiv에 게시한 'DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection' 논문에 대한 자세한 리뷰입니다.

#Review #AIGC Detection #Diffusion Models #Image Editing #Semantic Segmentation #Localization #Model Attribution #Benchmark #Multi-turn Editing

2025년 11월 25일

[논문리뷰] UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

arXiv에 게시된 'UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Diffusion Transformers #4K Resolution #Aspect Ratio Extrapolation #Data-Model Co-Design #VAE Post-training #Positional Encoding #Diffusion Models

2025년 11월 24일

[논문리뷰] SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis

Hongwen Zhang이 arXiv에 게시한 'SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Hand-Object Interaction #Multi-view Video Generation #4D Motion Synthesis #Diffusion Models #Spatio-temporal Consistency #Geometric Consistency #Appearance and Motion Joint Modeling

2025년 11월 24일

[논문리뷰] Controllable Layer Decomposition for Reversible Multi-Layer Image Generation

arXiv에 게시된 'Controllable Layer Decomposition for Reversible Multi-Layer Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Controllable Layer Decomposition #Diffusion Models #Multi-Layer Image Generation #Layer Separation #Bounding Box Guidance #Generative AI #Image Editing

2025년 11월 24일

[논문리뷰] Taming Generative Synthetic Data for X-ray Prohibited Item Detection

Renshuai Tao이 arXiv에 게시한 'Taming Generative Synthetic Data for X-ray Prohibited Item Detection' 논문에 대한 자세한 리뷰입니다.

#Review #X-ray Security #Synthetic Data Generation #Diffusion Models #Object Detection #Cross-Attention #Image Inpainting #Data Augmentation

2025년 11월 23일

[논문리뷰] Planning with Sketch-Guided Verification for Physics-Aware Video Generation

Shayegan Omidshafiei이 arXiv에 게시한 'Planning with Sketch-Guided Verification for Physics-Aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Motion Planning #Physics-Aware AI #Multimodal Verification #Diffusion Models #Test-Time Optimization #Sketch-Guided

2025년 11월 23일

[논문리뷰] Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Vladimir Arkhipkin이 arXiv에 게시한 'Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Video Generation #Diffusion Models #Flow Matching #Diffusion Transformer #NABLA #RLHF #Supervised Fine-tuning

2025년 11월 19일

[논문리뷰] A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space

arXiv에 게시된 'A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space' 논문에 대한 자세한 리뷰입니다.

#Review #Code-to-Style Generation #Discrete Style Space #Style Codebook #Autoregressive Model #Diffusion Models #Visual Stylization #Generative AI

2025년 11월 18일

[논문리뷰] EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation

Zeyu Wang이 arXiv에 게시한 'EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Dataset #Emotion Recognition #Video Generation #Affective Computing #Stylized Media #Diffusion Models #Video Understanding #Text-to-Video

2025년 11월 16일

[논문리뷰] Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance

Kwanyoung Kim이 arXiv에 게시한 'Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Guidance Sampling #Optimal Transport #Sinkhorn Algorithm #Self-Attention #Adversarial Perturbation #Image Generation #ControlNet

2025년 11월 12일

[논문리뷰] Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions

arXiv에 게시된 'Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Structured Captions #LLM Fusion #Controllability #Image Generation Evaluation #Diffusion Models #DimFusion #TaBR

2025년 11월 10일

[논문리뷰] Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

Zhao Xu이 arXiv에 게시한 'Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Direct Preference Optimization (DPO)#Safeguarded Learning #Text-to-Image Generation #Preference Alignment #Generative Models #Stable Diffusion

2025년 11월 10일

[논문리뷰] DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Kostas Daniilidis이 arXiv에 게시한 'DIMO: Diverse 3D Motion Generation for Arbitrary Objects' 논문에 대한 자세한 리뷰입니다.

#Review #3D Motion Generation #Generative Models #Arbitrary Objects #Neural Key Points #Latent Space #4D Content Generation #Diffusion Models #3D Gaussian Splatting

2025년 11월 10일

[논문리뷰] EVTAR: End-to-End Try on with Additional Unpaired Visual Reference

arXiv에 게시된 'EVTAR: End-to-End Try on with Additional Unpaired Visual Reference' 논문에 대한 자세한 리뷰입니다.

#Review #Virtual Try-on #Diffusion Models #End-to-End Learning #Reference Images #Unpaired Data #Flow Matching #Transformer Architecture #Generative AI

2025년 11월 9일

[논문리뷰] iFlyBot-VLA Technical Report

Jiajia wu이 arXiv에 게시한 'iFlyBot-VLA Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Robotics #Imitation Learning #Latent Actions #Diffusion Models #Dual-Arm Manipulation #Pretraining #Flow-Matching

2025년 11월 9일

[논문리뷰] Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation

arXiv에 게시된 'Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Direct Preference Optimization #SFT Regularization #GT-Pair #Memory Optimization #Diffusion Models #I2V #T2V

2025년 11월 9일

[논문리뷰] Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer

arXiv에 게시된 'Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #fMRI #Image Reconstruction #Brain-Computer Interface #Transformer #Diffusion Models #Neural Decoding #Cross-Subject Learning #Deep Image Prior

2025년 11월 9일

[논문리뷰] Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

arXiv에 게시된 'Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA)#Diffusion Models #Discrete Denoising #Multimodal Learning #Robotics #Embodied AI #Joint Generation #Action Prediction

2025년 11월 9일

[논문리뷰] UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

arXiv에 게시된 'UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback' 논문에 대한 자세한 리뷰입니다.

#Review #Relighting #Diffusion Models #Flow Matching #Physics-Plausible Feedback #Image-to-Video #Geometric Supervision #Path Consistency Learning #LumosBench

2025년 11월 9일

[논문리뷰] MotionStream: Real-Time Video Generation with Interactive Motion Controls

arXiv에 게시된 'MotionStream: Real-Time Video Generation with Interactive Motion Controls' 논문에 대한 자세한 리뷰입니다.

#Review #Real-Time Video Generation #Motion Control #Diffusion Models #Autoregressive Generation #Self-Forcing #Attention Sink #Streaming Inference #Video Distillation

2025년 11월 9일

[논문리뷰] Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model

Jinwoo Shin이 arXiv에 게시한 'Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #World Models #Diffusion Models #Multimodal Learning #Robotics #Asynchronous Sampling #Diffusion Transformers

2025년 11월 9일

[논문리뷰] Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

Olga Russakovsky이 arXiv에 게시한 'Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Synthesis #Synthetic Data Generation #Fine-Grained Classification #Few-Shot Learning #Diffusion Models #Contextual Conditioning #Causal Intervention

2025년 11월 9일

[논문리뷰] The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

arXiv에 게시된 'The Quest for Generalizable Motion Generation: Data, Model, and Evaluation' 논문에 대한 자세한 리뷰입니다.

#Review #Motion Generation #Generalization #Diffusion Models #Transformer #Large-scale Dataset #Benchmark #Multimodal Learning #Video Generation

2025년 10월 31일

[논문리뷰] FullPart: Generating each 3D Part at Full Resolution

Chenjian Gao이 arXiv에 게시한 'FullPart: Generating each 3D Part at Full Resolution' 논문에 대한 자세한 리뷰입니다.

#Review #3D Part Generation #Full Resolution #Implicit Representation #Explicit Representation #Voxel Grid #Diffusion Models #PartVerse-XL #Center-Corner Encoding

2025년 10월 31일

[논문리뷰] Exploring Conditions for Diffusion models in Robotic Control

arXiv에 게시된 'Exploring Conditions for Diffusion models in Robotic Control' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Robotic Control #Imitation Learning #Task-Adaptive Representations #Visual Prompts #Text-to-Image #Conditioning #Behavior Cloning

2025년 10월 31일

[논문리뷰] VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning

Xiaoyu Shi이 arXiv에 게시한 'VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning' 논문에 대한 자세한 리뷰입니다.

#Review #VFX Generation #In-Context Learning #Diffusion Models #Video Generation #Generalization #Attention Mask #One-Shot Adaptation

2025년 10월 30일

[논문리뷰] The Principles of Diffusion Models

Stefano Ermon이 arXiv에 게시한 'The Principles of Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Generative AI #Variational Autoencoder #Energy-Based Models #Normalizing Flows #Score-Based SDEs #Flow Matching #Fokker-Planck Equation

2025년 10월 30일

[논문리뷰] Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

arXiv에 게시된 'Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #Synthetic Data Generation #Autonomous Driving #Perception Tasks #Diffusion Models #3D Asset Editing #World Model #Data Augmentation #nuScenes

2025년 10월 30일

[논문리뷰] RegionE: Adaptive Region-Aware Generation for Efficient Image Editing

Peng Ye이 arXiv에 게시한 'RegionE: Adaptive Region-Aware Generation for Efficient Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Instruction-based Image Editing #Diffusion Models #Efficient Inference #Region-Aware Generation #Adaptive Caching #Spatial Redundancy #Temporal Redundancy

2025년 10월 30일

[논문리뷰] ODesign: A World Model for Biomolecular Interaction Design

Qinghan Wang이 arXiv에 게시한 'ODesign: A World Model for Biomolecular Interaction Design' 논문에 대한 자세한 리뷰입니다.

#Review #Biomolecular Interaction Design #Generative AI #World Model #Multimodal Molecular Design #All-atom Generation #Diffusion Models #Protein Design #Nucleic Acid Design

2025년 10월 30일

[논문리뷰] UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

arXiv에 게시된 'UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset' 논문에 대한 자세한 리뷰입니다.

#Review #Ultra-High-Resolution #Text-to-Image Generation #Diffusion Models #Large-Scale Dataset #Frequency-Aware Training #Detail Enhancement #Image Synthesis

2025년 10월 29일

[논문리뷰] EchoDistill: Bidirectional Concept Distillation for One-Step Diffusion Personalization

Yaxing Wang이 arXiv에 게시한 'EchoDistill: Bidirectional Concept Distillation for One-Step Diffusion Personalization' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #One-Step Generation #Model Personalization #Knowledge Distillation #Bidirectional Learning #Text-to-Image Generation #Concept Learning

2025년 10월 28일

[논문리뷰] Visual Diffusion Models are Geometric Solvers

Or Patashnik이 arXiv에 게시한 'Visual Diffusion Models are Geometric Solvers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Geometric Problem Solving #Inscribed Square Problem #Steiner Tree Problem #Maximum Area Polygonization #Image Generation #Pixel Space

2025년 10월 27일

[논문리뷰] Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation

arXiv에 게시된 'Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Reinforcement Learning #GRPO #Flow Matching #Chunk-level Optimization #Temporal Dynamics #Diffusion Models

2025년 10월 27일

[논문리뷰] RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling

arXiv에 게시된 'RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Video Generation #Prompt Optimization #Large Language Models (LLM)#Test-Time Scaling #Retrieval-Augmented Generation #Diffusion Models #Data Alignment

2025년 10월 27일

[논문리뷰] Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video

arXiv에 게시된 'Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Audio #Video-to-Audio #Foley Synthesis #Diffusion Models #Cross-Attention #Frozen Backbones #Video Embeddings #Rotary Position Embeddings

2025년 10월 27일

[논문리뷰] Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

arXiv에 게시된 'Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets' 논문에 대한 자세한 리뷰입니다.

#Review #3D Asset Generation #Simulation-Ready Assets #Diffusion Models #Physically Based Rendering (PBR)#Embodied AI #Robotic Simulation #Image-to-3D #Foundation Model

2025년 10월 24일

[논문리뷰] LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas

arXiv에 게시된 'LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Personalization #Diffusion Models #Interactive Control #Multi-Subject Composition #Layered Canvas #Spatial Control #Image Editing

2025년 10월 24일

[논문리뷰] HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

arXiv에 게시된 'HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Video Generation #Multi-Shot Video #Narrative Coherence #Diffusion Models #Self-Attention #Cinematic AI #Video Consistency #Directorial Control

2025년 10월 24일

[논문리뷰] DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

arXiv에 게시된 'DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Transformer Architecture #Positional Encoding #High-Resolution Image Generation #Extrapolation #Dynamic Adaptation #Training-Free

2025년 10월 24일

[논문리뷰] DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Roi Reichart이 arXiv에 게시한 'DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models' 논문에 대한 자세한 리뷰입니다.

#Review #Semantic Leakage #Text-to-Image Models #Attention Control #Inference-time Mitigation #Diffusion Models #Evaluation Dataset #Self-Attention

2025년 10월 23일

[논문리뷰] Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling

Dim P. Papadopoulos이 arXiv에 게시한 'Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Autoregressive Models #Diffusion Models #Inference Time Scaling #Beam Search #Image Generation #Text-to-Image Synthesis #Discrete Latent Space

2025년 10월 21일

[논문리뷰] Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

arXiv에 게시된 'Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Reinforcement Learning #MLLM #Policy Optimization #Finetuning #Reward Modeling #Human Alignment

2025년 10월 21일

[논문리뷰] PICABench: How Far Are We from Physically Realistic Image Editing?

Kaiwen Zhu이 arXiv에 게시한 'PICABench: How Far Are We from Physically Realistic Image Editing?' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Physical Realism #Benchmark #VLM-as-a-Judge #Synthetic Data #Physics-Aware AI #Diffusion Models #Evaluation Metrics

2025년 10월 21일

[논문리뷰] Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Chung-Ho Wu이 arXiv에 게시한 'Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Synthesis #Gaussian Splatting #Satellite Imagery #Diffusion Models #Urban Modeling #Novel View Synthesis #Curriculum Learning #Real-time Rendering

2025년 10월 20일

[논문리뷰] Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Hao Ouyang이 arXiv에 게시한 'Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset' 논문에 대한 자세한 리뷰입니다.

#Review #Video Editing #Instruction-Based Editing #Synthetic Data Generation #Dataset #Curriculum Learning #Diffusion Models #Vision-Language Models

2025년 10월 20일

[논문리뷰] LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

arXiv에 게시된 'LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal' 논문에 대한 자세한 리뷰입니다.

#Review #Lens Flare Removal #Diffusion Models #Image Outpainting #Deep Learning #Image Restoration #Preprocessing #LoRA

2025년 10월 20일

[논문리뷰] Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation

Junsheng Yu이 arXiv에 게시한 'Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Layout Generation #Vision-guided #Diffusion Models #Scene Graph #Asset Retrieval #Pose Estimation #High-Quality Assets #AI Content Creation

2025년 10월 20일

[논문리뷰] pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

arXiv에 게시된 'pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Flow Matching #Generative Models #Model Distillation #Imitation Learning #Few-Step Generation #Policy-Based AI #Text-to-Image

2025년 10월 17일

[논문리뷰] RealDPO: Real or Not Real, that is the Preference

Chenyang Si이 arXiv에 게시한 'RealDPO: Real or Not Real, that is the Preference' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Direct Preference Optimization #Preference Learning #Real Data #Human Motion Synthesis #RealDPO #RealAction-5K

2025년 10월 17일

[논문리뷰] Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation

arXiv에 게시된 'Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation' 논문에 대한 자세한 리뷰입니다.

#Review #Human-human Interaction #Pose Animation #Diffusion Models #Generative AI #Motion Synthesis #Interactive Poses #Temporal Priors #Spatial Priors

2025년 10월 17일

[논문리뷰] Learning an Image Editing Model without Image Editing Pairs

arXiv에 게시된 'Learning an Image Editing Model without Image Editing Pairs' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Vision-Language Models (VLMs)#No-Pair Training #Few-step Generation #Distribution Matching #Gradient-based Optimization

2025년 10월 17일

[논문리뷰] ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

arXiv에 게시된 'ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Test-Time Search #Diffusion Models #Semantic Dependency #Adaptive Reward #Evaluation Benchmark #Prompt-Guided

2025년 10월 17일

[논문리뷰] DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation

arXiv에 게시된 'DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Generation #Dialect Robustness #Text-to-Image #Text-to-Video #Benchmarking #Diffusion Models #Text Encoder Tuning #Low-Resource Dialects

2025년 10월 17일

[논문리뷰] PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Hengshuang Zhao이 arXiv에 게시한 'PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physical Plausibility #Reinforcement Learning #Direct Preference Optimization #Physical Representation #Diffusion Models #World Models #Image-to-Video

2025년 10월 16일

[논문리뷰] InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

Yilun Chen이 arXiv에 게시한 'InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy' 논문에 대한 자세한 리뷰입니다.

#Review #Robotics #Vision-Language-Action (VLA)#Spatial Grounding #Generalist Policy #Multimodal Learning #Instruction Following #Simulation-to-Real #Diffusion Models

2025년 10월 16일

[논문리뷰] FlashWorld: High-quality 3D Scene Generation within Seconds

Chunchao Guo이 arXiv에 게시한 'FlashWorld: High-quality 3D Scene Generation within Seconds' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Generation #Diffusion Models #Multi-View Synthesis #3D Gaussian Splatting #Knowledge Distillation #Real-time Generation #High-Quality Rendering #Cross-modal Training

2025년 10월 16일

[논문리뷰] CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving

Jingcheng Ni이 arXiv에 게시한 'CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Driving #Video Generation #Diffusion Models #Spatial-Temporal Reconstruction #3D Gaussian Splatting #Variational Autoencoder #World Modeling #Multi-View Video

2025년 10월 16일

[논문리뷰] UniFusion: Vision-Language Model as Unified Encoder in Image Generation

arXiv에 게시된 'UniFusion: Vision-Language Model as Unified Encoder in Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Model #Unified Encoder #Image Generation #Diffusion Models #Multimodal Learning #Text-to-Image #Image Editing #Zero-shot Learning

2025년 10월 15일

[논문리뷰] Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models

arXiv에 게시된 'Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Generative Models #Guidance #On-Manifold Sampling #Temporal Alignment #Score Approximation Error #Training-Free Guidance

2025년 10월 15일

[논문리뷰] Robot Learning: A Tutorial

arXiv에 게시된 'Robot Learning: A Tutorial' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Reinforcement Learning #Imitation Learning #Behavioral Cloning #Vision-Language-Action Models #Diffusion Models #Transformers #LeRobot

2025년 10월 15일

[논문리뷰] FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Yihao Liu이 arXiv에 게시한 'FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution' 논문에 대한 자세한 리뷰입니다.

#Review #Video Super-Resolution (VSR)#Diffusion Models #Real-time VSR #Streaming VSR #Sparse Attention #Distillation #Conditional Decoder #High-resolution

2025년 10월 15일

[논문리뷰] Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

arXiv에 게시된 'Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training' 논문에 대한 자세한 리뷰입니다.

#Review #Pixel-space Generative Models #Diffusion Models #Consistency Models #Self-supervised Pre-training #End-to-end Training #Image Generation #FID #Representation Learning

2025년 10월 15일

[논문리뷰] TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control

Adityan Jothi이 arXiv에 게시한 'TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Conditional Generation #LoRA #Hypernetwork #Dynamic Weight Adaptation #Generative AI #Controllable Generation

2025년 10월 13일

[논문리뷰] UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections

Boqian Li이 arXiv에 게시한 'UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections' 논문에 대한 자세한 리뷰입니다.

#Review #3D Human Reconstruction #Unconstrained Photos #Data Rectifier #Multi-View Generation #Pose-Correlated Feature Aggregation #SMPL-X #Diffusion Models #Virtual Try-On

2025년 10월 10일

[논문리뷰] Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

arXiv에 게시된 'Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Sounding Video Generation #Diffusion Models #Dual-tower Architecture #Cross-modal Fusion #Visual Grounding #Hierarchical Captioning #Cross-Attention

2025년 10월 10일

[논문리뷰] Reinforcing Diffusion Models by Direct Group Preference Optimization

Jing Tang이 arXiv에 게시한 'Reinforcing Diffusion Models by Direct Group Preference Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Reinforcement Learning #Preference Optimization #Group Preference #Direct Preference Optimization #ODE Samplers #Efficient Training

2025년 10월 10일

[논문리뷰] InstructX: Towards Unified Visual Editing with MLLM Guidance

Xinghui Li이 arXiv에 게시한 'InstructX: Towards Unified Visual Editing with MLLM Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Editing #MLLM Guidance #Diffusion Models #Image Editing #Video Editing #Unified Framework #Multimodal AI #Instruction-based Editing

2025년 10월 10일

[논문리뷰] Fidelity-Aware Data Composition for Robust Robot Generalization

Liliang Chen이 arXiv에 게시한 'Fidelity-Aware Data Composition for Robust Robot Generalization' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Generalization #Data Augmentation #Out-of-Distribution (OOD)#Shortcut Learning #Information Fidelity #Data Composition #Diffusion Models #Multi-View Video Synthesis

2025년 10월 10일

[논문리뷰] WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation

arXiv에 게시된 'WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #4D World Models #Robotic Manipulation #Video Generation #Multi-view Synthesis #Visual-Language-Action (VLA)#Geometric Consistency #Diffusion Models #Wrist-View

2025년 10월 9일

[논문리뷰] StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

arXiv에 게시된 'StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #State Representation #Motion Representation #Diffusion Models #Unsupervised Learning #World Modeling #Vision-Language Models #Latent Action

2025년 10월 9일

[논문리뷰] OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

arXiv에 게시된 'OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Network Pruning #One-Shot Pruning #Optimal Brain Surgeon (OBS)#Model Compression #Timestep-Aware Hessian #Structured Pruning

2025년 10월 9일

[논문리뷰] Bridging Text and Video Generation: A Survey

G. Maragatham이 arXiv에 게시한 'Bridging Text and Video Generation: A Survey' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Video Generation #Generative Models #Diffusion Models #GANs #VAEs #Video Synthesis #Survey #Evaluation Metrics

2025년 10월 9일

[논문리뷰] LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

Zheng Zhan이 arXiv에 게시한 'LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Memory Efficiency #Inference Acceleration #Training-Free #Cache Mechanism #GPU Optimization

2025년 10월 8일

[논문리뷰] Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

arXiv에 게시된 'Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Models #Equilibrium Dynamics #Energy-Based Models (EBMs)#Flow Matching #Diffusion Models #Optimization-Based Sampling #Image Generation

2025년 10월 8일

[논문리뷰] Deforming Videos to Masks: Flow Matching for Referring Video Segmentation

Chengzu Li이 arXiv에 게시한 'Deforming Videos to Masks: Flow Matching for Referring Video Segmentation' 논문에 대한 자세한 리뷰입니다.

#Review #Referring Video Object Segmentation #Flow Matching #Video Segmentation #Generative Models #Text-to-Video #Continuous Flow #Diffusion Models

2025년 10월 8일

[논문리뷰] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

Paul Debevec이 arXiv에 게시한 'VChain: Chain-of-Visual-Thought for Reasoning in Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Chain-of-Thought #Multimodal Models #Reasoning #Inference-Time Tuning #Sparse Supervision #Diffusion Models #Keyframe Generation

2025년 10월 7일

[논문리뷰] SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder

Or Patashnik이 arXiv에 게시한 'SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Sparse Autoencoder (SAE)#Text-to-Image #Disentangled Control #Continuous Control #Token-level Manipulation #Text Embeddings

2025년 10월 7일

[논문리뷰] Factuality Matters: When Image Generation and Editing Meet Structured Visuals

Boxiang Qiu이 arXiv에 게시한 'Factuality Matters: When Image Generation and Editing Meet Structured Visuals' 논문에 대한 자세한 리뷰입니다.

#Review #Structured Visuals #Image Generation #Image Editing #Multimodal Reasoning #Factual Fidelity #Chain-of-Thought #Evaluation Benchmark #Diffusion Models

2025년 10월 7일

[논문리뷰] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

arXiv에 게시된 'ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Video Generation #Temporal Reasoning #World Simulation #Physical Consistency #Diffusion Models #Generative Models

2025년 10월 7일

[논문리뷰] Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs

arXiv에 게시된 'Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Models #Diffusion Models #Preference Optimization #LLMs #RLHF #Prompt Editing #Free Lunch Alignment #TDPO #TKTO

2025년 10월 6일

[논문리뷰] Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

arXiv에 게시된 'Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Flow-based Models #Robotics Control #Policy Composition #Test-time Optimization #Score-based Models #Training-free

2025년 10월 6일

[논문리뷰] Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Jong Chul Ye이 arXiv에 게시한 'Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents' 논문에 대한 자세한 리뷰입니다.

#Review #Consistency Models #Generative Models #Manifold Learning #Tangent Alignment #Diffusion Models #Training Dynamics #Manifold Feature Distance

2025년 10월 6일

[논문리뷰] BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration

Xiangyang Xia이 arXiv에 게시한 'BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Subject Consistency #Cross-Modal Integration #Diffusion Models #Multimodal LLM #Diffusion Transformer #Text-to-Video

2025년 10월 2일

[논문리뷰] d^2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching

Jiarui Wang이 arXiv에 게시한 'd^2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Large Language Models (LLMs)#Inference Acceleration #KV Cache #Bidirectional Attention #Adaptive Caching #Token Selection

2025년 10월 1일

[논문리뷰] MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

Limin Wang이 arXiv에 게시한 'MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Image-to-Video Generation #Motion Transfer #Retrieval-Augmented Generation (RAG)#In-Context Learning #Diffusion Models #Video Diffusion #Motion Realism

2025년 10월 1일

[논문리뷰] MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification

Zhiming Luo이 arXiv에 게시한 'MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification' 논문에 대한 자세한 리뷰입니다.

#Review #Adversarial Purification #Diffusion Models #Frequency Domain #Adaptive Noise Injection #Robustness #Image Security #Magnitude Spectrum

2025년 10월 1일

[논문리뷰] IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

arXiv에 게시된 'IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Multimodal Alignment #MLLM #Image Re-generation #Preference Learning #Implicit Guidance #Text-to-Image

2025년 10월 1일

[논문리뷰] DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

arXiv에 게시된 'DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Models #Video Autoencoder #Deep Compression #Model Acceleration #Fine-tuning #Latent Space #Temporal Modeling

2025년 10월 1일

[논문리뷰] X-Streamer: Unified Human World Modeling with Audiovisual Interaction

Guoxian Song이 arXiv에 게시한 'X-Streamer: Unified Human World Modeling with Audiovisual Interaction' 논문에 대한 자세한 리뷰입니다.

#Review #Digital Human #Multimodal AI #Real-time Streaming #Video Generation #Diffusion Models #Transformer Architecture #Audiovisual Synchronization #World Modeling

2025년 9월 29일

[논문리뷰] WoW: Towards a World omniscient World model Through Embodied Interaction

Weishi Mi이 arXiv에 게시한 'WoW: Towards a World omniscient World model Through Embodied Interaction' 논문에 대한 자세한 리뷰입니다.

#Review #World Model #Embodied AI #Robotics #Diffusion Models #Physical Reasoning #Vision Language Models #Interaction Data #Self-Optimization

2025년 9월 29일

[논문리뷰] Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

Peter Wonka이 arXiv에 게시한 'Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Subject-Driven Generation #Visual Inconsistency Detection #Feature Disentanglement #Diffusion Models #Semantic Correspondence #Evaluation Metric #Spatial Localization #Contrastive Learning

2025년 9월 29일

[논문리뷰] LongLive: Real-time Interactive Long Video Generation

arXiv에 게시된 'LongLive: Real-time Interactive Long Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Long Video Generation #Real-time #Interactive AI #Autoregressive Models #KV Cache #Streaming Tuning #Attention Sink #Diffusion Models

2025년 9월 29일

[논문리뷰] HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models

Romann M. Weber이 arXiv에 게시한 'HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Sampling #Generative AI #Image Generation #Plug-and-Play #Training-Free #Guidance #Momentum-Based Methods

2025년 9월 29일

[논문리뷰] FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

Linghe Kong이 arXiv에 게시한 'FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Text-Guided Image Editing #Diffusion Models #Real-Time Editing #One-Step Inversion #Attention Control #Background Preservation #Semantic Disentanglement

2025년 9월 29일

[논문리뷰] SD3.5-Flash: Distribution-Guided Distillation of Generative Flows

Yi-Zhe Song이 arXiv에 게시한 'SD3.5-Flash: Distribution-Guided Distillation of Generative Flows' 논문에 대한 자세한 리뷰입니다.

#Review #Generative AI #Image Generation #Diffusion Models #Rectified Flow #Model Distillation #Few-Step Generation #Computational Efficiency #Prompt Alignment

2025년 9월 26일

[논문리뷰] Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Bowen Zhang이 arXiv에 게시한 'Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets' 논문에 대한 자세한 리뷰입니다.

#Review #3D Generation #Controllable Generation #Multi-modal Conditioning #Diffusion Models #Point Clouds #Voxels #Bounding Boxes #Skeletons #Hunyuan3D

2025년 9월 26일

[논문리뷰] Does FLUX Already Know How to Perform Physically Plausible Image Composition?

Chen Zhao이 arXiv에 게시한 'Does FLUX Already Know How to Perform Physically Plausible Image Composition?' 논문에 대한 자세한 리뷰입니다.

#Review #Image Composition #Diffusion Models #Training-Free #Physically Plausible #FLUX #Adapter #Guidance #Benchmark

2025년 9월 26일

[논문리뷰] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Yiming Huang이 arXiv에 게시한 'PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physics-Grounded #Controllable Generation #Diffusion Models #Point Cloud Trajectories #Material Simulation #Generative Physics

2025년 9월 25일

[논문리뷰] CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

Rui Qian이 arXiv에 게시한 'CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching' 논문에 대한 자세한 리뷰입니다.

#Review #Flow Matching #Conditional Generative Models #Reparameterization #Mode Collapse #Image Generation #Latent Space Alignment #Diffusion Models

2025년 9월 24일

[논문리뷰] OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

Pengze Zhang이 arXiv에 게시한 'OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Insertion #Diffusion Models #Diffusion Transformers #Mask-Free #Data Augmentation #Progressive Training #Preference Optimization #Video Generation

2025년 9월 23일

[논문리뷰] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Qinsheng Zhang이 arXiv에 게시한 'DiffusionNFT: Online Diffusion Reinforcement with Forward Process' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Reinforcement Learning #Online RL #Flow Matching #Forward Process #CFG-free #Image Generation #Negative-Aware FineTuning

2025년 9월 23일

[논문리뷰] SPATIALGEN: Layout-guided 3D Indoor Scene Generation

Yongsen Mao이 arXiv에 게시한 'SPATIALGEN: Layout-guided 3D Indoor Scene Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Generation #Layout Guidance #Diffusion Models #Multi-view Synthesis #Synthetic Dataset #Indoor Environments #Gaussian Splatting #Semantic Consistency

2025년 9월 22일

[논문리뷰] Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

Hui Zhang이 arXiv에 게시한 'Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied AI #Human-Robot Interaction #Multi-turn Dialogue #Instruction Following #Vision-Language Models #Diffusion Models #Ambiguity Resolution #Low-level Actions

2025년 9월 22일

[논문리뷰] Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

Mingyang Huang이 arXiv에 게시한 'Wan-Animate: Unified Character Animation and Replacement with Holistic Replication' 논문에 대한 자세한 리뷰입니다.

#Review #Character Animation #Video Replacement #Diffusion Models #Transformer #DiT #Relighting LoRA #Holistic Replication #Open-Source

2025년 9월 18일

[논문리뷰] Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

Lixin Xu이 arXiv에 게시한 'Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Asset Generation #AI Pipeline #Generative AI #Game Development #Diffusion Models #Neural Modules #Retopology #UV Unwrapping

2025년 9월 17일

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

Vincent Sitzmann이 arXiv에 게시한 'Locality in Image Diffusion Models Emerges from Data Statistics' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Locality #Data Statistics #Optimal Denoiser #Wiener Filter #Sensitivity Fields #Generative Models #Inductive Bias

2025년 9월 16일

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

Lionel M. Ni이 arXiv에 게시한 'LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Multi-Modal Transformers #Drag-based Editing #Explicit Correspondence #Attention Control #Identity Preservation #Training-Free

2025년 9월 16일

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

Yunhan Yang이 arXiv에 게시한 'X-Part: high fidelity and structure coherent shape decomposition' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Decomposition #Diffusion Models #Part-level Generation #Controllable Generation #Bounding Box Prompts #Semantic Features #Interactive Editing #Generative AI

2025년 9월 15일

[논문리뷰] InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

Song Guo이 arXiv에 게시한 'InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Image Synthesis #Resolution-Agnostic #Diffusion Models #Latent Space #VAE Decoder #High-Resolution Image Generation #Generative AI #Transformer Architecture

2025년 9월 15일

[논문리뷰] FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

Fabian Otto이 arXiv에 게시한 'FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies' 논문에 대한 자세한 리뷰입니다.

#Review #Generalist Robot Policies #Vision-Language-Action Models #Efficient AI #Imitation Learning #Diffusion Models #Intermediate Fusion #Robotics

2025년 9월 15일

[논문리뷰] HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Zhuowei Chen이 arXiv에 게시한 'HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning' 논문에 대한 자세한 리뷰입니다.

#Review #Human-Centric Video Generation #Multimodal Conditioning #Text-to-Video #Image-to-Video #Audio-to-Video #Diffusion Models #Subject Preservation #Audio-Visual Synchronization #Progressive Training

2025년 9월 12일

[논문리뷰] UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

Fei Ding이 arXiv에 게시한 'UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward' 논문에 대한 자세한 리뷰입니다.

#Review #Image Customization #Multi-Identity Generation #Identity Consistency #Identity Confusion #Reinforcement Learning #Diffusion Models #Matching Reward #Global Assignment

2025년 9월 10일

[논문리뷰] Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

Diana Marculescu이 arXiv에 게시한 'Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Quantization #Few-Step Generation #Model Compression #Noise Scheduling #Post-Training Quantization #Image Quality Metrics #Latent Consistency Models

2025년 9월 10일

[논문리뷰] Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

Yingfang Zhang이 arXiv에 게시한 'Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Reinforcement Learning #Human Preference #Text-to-Image Generation #Reward Hacking #Direct-Align #SRPO #Fine-Grained Control #Flow Matching Models

2025년 9월 10일

[논문리뷰] Interleaving Reasoning for Better Text-to-Image Generation

Shixiang Tang이 arXiv에 게시한 'Interleaving Reasoning for Better Text-to-Image Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Interleaving Reasoning #Multimodal Learning #Visual Quality #Fine-grained Detail #Diffusion Models #Self-Correction

2025년 9월 9일

[논문리뷰] Set Block Decoding is a Language Model Inference Accelerator

Jeremy Reizenstein이 arXiv에 게시한 'Set Block Decoding is a Language Model Inference Accelerator' 논문에 대한 자세한 리뷰입니다.

#Review #Language Model Inference #Acceleration #Set Block Decoding #Next Token Prediction #Masked Token Prediction #Parallel Decoding #KV-caching #Diffusion Models

2025년 9월 8일

[논문리뷰] LuxDiT: Lighting Estimation with Video Diffusion Transformer

Sanja Fidler이 arXiv에 게시한 'LuxDiT: Lighting Estimation with Video Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Lighting Estimation #HDR Environment Map #Diffusion Models #Video Transformer #Low-Rank Adaptation #Generative Models #Synthetic Data

2025년 9월 8일

[논문리뷰] Transition Models: Rethinking the Generative Learning Objective

Yangguang Li이 arXiv에 게시한 'Transition Models: Rethinking the Generative Learning Objective' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Models #Diffusion Models #Training Objective #Continuous-Time Dynamics #State Transition #Few-Step Generation #Scalable Training #Image Generation

2025년 9월 5일

[논문리뷰] Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

Hanbyul Joo이 arXiv에 게시한 'Durian: Dual Reference-guided Portrait Animation with Attribute Transfer' 논문에 대한 자세한 리뷰입니다.

#Review #Portrait Animation #Attribute Transfer #Diffusion Models #Dual Reference Networks #Zero-shot Learning #Self-Reconstruction #Facial Editing

2025년 9월 5일

[논문리뷰] MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

Hualiang Wang이 arXiv에 게시한 'MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Subject Generation #Personalized Image Synthesis #Semantic Correspondence #Attention Disentanglement #Diffusion Models #Identity Preservation #Dataset

2025년 9월 4일

[논문리뷰] GenCompositor: Generative Video Compositing with Diffusion Transformer

Lingen Li이 arXiv에 게시한 'GenCompositor: Generative Video Compositing with Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Video Compositing #Diffusion Transformer #Generative Models #Video Editing #Position Embedding #Diffusion Models #Masked Token Injection #Video Harmonization

2025년 9월 3일

[논문리뷰] FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models

Zhen Wang이 arXiv에 게시한 'FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Virtual Try-On #Diffusion Models #Cacheable Architecture #Multi-Reference #Semi-Attention #Efficiency #Image Synthesis

2025년 9월 3일

[논문리뷰] USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

Jiahe Tian이 arXiv에 게시한 'USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Style-Driven Generation #Subject-Driven Generation #Disentangled Representation #Reward Learning #Cross-Task Learning #Diffusion Models #Image Customization #Unified Framework

2025년 8월 29일

[논문리뷰] Collaborative Multi-Modal Coding for High-Quality 3D Generation

Ziwei Liu이 arXiv에 게시한 'Collaborative Multi-Modal Coding for High-Quality 3D Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D Generation #Multi-modal Learning #Diffusion Models #Triplane Representation #Collaborative Coding #Image-to-3D #Latent Space

2025년 8월 29일

[논문리뷰] MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

Yan Zhou이 arXiv에 게시한 'MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Generation #Digital Human Synthesis #Real-time Video Generation #Autoregressive LLM #Diffusion Models #Deep Compression Autoencoder #Exposure Bias Mitigation #Streaming Inference

2025년 8월 28일

[논문리뷰] AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Yixiao Ge이 arXiv에 게시한 'AudioStory: Generating Long-Form Narrative Audio with Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Audio #Long-Form Audio Generation #Large Language Models #Narrative Reasoning #Diffusion Models #Multimodal AI #Progressive Training

2025년 8월 28일

[논문리뷰] Wan-S2V: Audio-Driven Cinematic Video Generation

Chaonan Ji이 arXiv에 게시한 'Wan-S2V: Audio-Driven Cinematic Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Driven Video Generation #Cinematic Video #Diffusion Models #Transformer Architecture #Long Video Consistency #Human Animation #Multimodal Control #Data Curation

2025년 8월 27일

[논문리뷰] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

Rui Chen이 arXiv에 게시한 'VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space' 논문에 대한 자세한 리뷰입니다.

#Review #3D Editing #Training-Free #Diffusion Models #Latent Space #3D Inversion #Contextual Feature Replacement #3D Consistency #Edit3D-Bench

2025년 8월 27일

[논문리뷰] CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

Ziwei Liu이 arXiv에 게시한 'CineScale: Free Lunch in High-Resolution Cinematic Visual Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #High-Resolution Generation #Image Generation #Video Generation #UNet Architecture #DiT Architecture #Scale Fusion #LoRA Fine-tuning

2025년 8월 27일

[논문리뷰] SpotEdit: Evaluating Visually-Guided Image Editing Methods

Ersin Yumer이 arXiv에 게시한 'SpotEdit: Evaluating Visually-Guided Image Editing Methods' 논문에 대한 자세한 리뷰입니다.

#Review #Visually-Guided Image Editing #Multimodal Models #Benchmark #Hallucination #Diffusion Models #Autoregressive Models #Evaluation Metrics

2025년 8월 26일

[논문리뷰] MV-RAG: Retrieval Augmented Multiview Diffusion

sagiebenaim이 arXiv에 게시한 'MV-RAG: Retrieval Augmented Multiview Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Retrieval Augmented Generation #Multiview Diffusion #Text-to-3D Generation #Out-of-Domain #Image Retrieval #3D Consistency #Diffusion Models #Hybrid Training

2025년 8월 26일

[논문리뷰] SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass

Ya Zhang이 arXiv에 게시한 'SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass' 논문에 대한 자세한 리뷰입니다.

#Review #3D Scene Generation #Single-Image Input #Feedforward Networks #Diffusion Models #Geometric Modeling #Texture Synthesis #Transformer #Feature Aggregation

2025년 8월 22일

[논문리뷰] Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

Hao Chen이 arXiv에 게시한 'Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #3D Editing #Multi-View Consistency #Diffusion Models #Sparse Input #Zero-Shot Learning #Scene Completion #Gaussian Splatting

2025년 8월 21일

[논문리뷰] S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

Meiqi Wu이 arXiv에 게시한 'S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Classifier-free Guidance #Self-Guidance #Training-Free #Stochastic Block-Dropping #Generative Models #Text-to-Image

2025년 8월 19일

[논문리뷰] Precise Action-to-Video Generation Through Visual Action Prompts

Minghan Qin이 arXiv에 게시한 'Precise Action-to-Video Generation Through Visual Action Prompts' 논문에 대한 자세한 리뷰입니다.

#Review #Action-to-Video Generation #Visual Action Prompts #Skeleton Representation #Human-Object Interaction #Robotic Manipulation #Cross-Domain Transfer #Diffusion Models

2025년 8월 19일

[논문리뷰] Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Yifan Zhang이 arXiv에 게시한 'Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model' 논문에 대한 자세한 리뷰입니다.

#Review #World Model #Interactive Video Generation #Real-Time AI #Diffusion Models #Auto-Regressive Generation #Data Pipeline #Self-Forcing #KV Caching

2025년 8월 19일

[논문리뷰] Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

Zixiang Gao이 arXiv에 게시한 'Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Relighting #Background Replacement #Generative Models #Diffusion Models #Temporal Consistency #Dataset Generation #Video Editing

2025년 8월 19일

[논문리뷰] 4DNeX: Feed-Forward 4D Generative Modeling Made Easy

Zeng Tao이 arXiv에 게시한 '4DNeX: Feed-Forward 4D Generative Modeling Made Easy' 논문에 대한 자세한 리뷰입니다.

#Review #4D Generation #Dynamic 3D #Generative Models #Diffusion Models #Single Image Input #Video Synthesis #Point Clouds #Dataset

2025년 8월 19일

[논문리뷰] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

Mu Xu이 arXiv에 게시한 'FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Driven Animation #Preference Optimization #Diffusion Models #Reward Modeling #Human Feedback #Multi-Objective Optimization #Timestep-Layer Adaptive

2025년 8월 18일

[논문리뷰] Story2Board: A Training-Free Approach for Expressive Storyboard Generation

Dani Lischinski이 arXiv에 게시한 'Story2Board: A Training-Free Approach for Expressive Storyboard Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Storyboard Generation #Text-to-Image #Diffusion Models #Training-Free #Character Consistency #Scene Diversity #Visual Storytelling

2025년 8월 14일

[논문리뷰] Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

Chen Li이 arXiv에 게시한 'Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Identity Preservation #Plug-and-Play #Diffusion Models #Self-Attention #Lightweight AI #Conditional Image Branch

2025년 8월 14일

[논문리뷰] Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Zeynep Akata이 arXiv에 게시한 'Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Hypernetworks #Test-Time Optimization #Reward-Guided Generation #Latent Space Optimization #LoRA #Generative AI

2025년 8월 14일

[논문리뷰] Matrix-3D: Omnidirectional Explorable 3D World Generation

Yuqi Li이 arXiv에 게시한 'Matrix-3D: Omnidirectional Explorable 3D World Generation' 논문에 대한 자세한 리뷰입니다.

#Review #3D World Generation #Panoramic Video Generation #3D Reconstruction #Diffusion Models #Gaussian Splatting #Dataset #Camera Control

2025년 8월 13일

[논문리뷰] CharacterShot: Controllable and Consistent 4D Character Animation

Fei Shen이 arXiv에 게시한 'CharacterShot: Controllable and Consistent 4D Character Animation' 논문에 대한 자세한 리뷰입니다.

#Review #4D Character Animation #Diffusion Models #Gaussian Splatting #Pose Control #Multi-view Synthesis #Temporal Consistency #Character Dataset

2025년 8월 13일

[논문리뷰] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

Xiaokun Feng이 arXiv에 게시한 'Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Effects #Video Generation #LoRA #Mixture of Experts #Spatial Control #Diffusion Models #Multi-VFX

2025년 8월 12일

[논문리뷰] Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

Hongyu Liu이 arXiv에 게시한 'Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Shape Transformation #Rectified Flow #Trajectory Divergence Map #Region Control #Generative Models #Diffusion Models

2025년 8월 12일

[논문리뷰] LightSwitch: Multi-view Relighting with Material-guided Diffusion

Shubham Tulsiani이 arXiv에 게시한 'LightSwitch: Multi-view Relighting with Material-guided Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-view Relighting #Diffusion Models #Material-guided #Inverse Rendering #3D Scene Reconstruction #Image Synthesis #Consistent Relighting

2025년 8월 11일

[논문리뷰] StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

Xiaobin Hu이 arXiv에 게시한 'StrandDesigner: Towards Practical Strand Generation with Sketch Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Strand Generation #Sketch Guidance #Diffusion Models #Multi-scale Learning #Adaptive Conditioning #3D Hair Modeling #Computer Graphics

2025년 8월 8일

[논문리뷰] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

Yifei Ji이 arXiv에 게시한 'Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression' 논문에 대한 자세한 리뷰입니다.

#Review #Image Compression #Diffusion Models #One-Step Decoding #Fidelity Guidance #Rate Annealing #VAE #Perceptual Quality

2025년 8월 8일

[논문리뷰] The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models

Elisabetta Rocchetti이 arXiv에 게시한 'The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Diffusion Models #Cross-Attention Analysis #Content-Style Disentanglement #Artistic Style Transfer #Explainable AI #SDXL

2025년 8월 7일

[논문리뷰] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

Feng Zhao이 arXiv에 게시한 'Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #4D Generation #Video-to-3D Synthesis #Gaussian Splatting #Diffusion Models #Latent Space Modeling #Variational Autoencoder #Temporal Coherence

2025년 8월 7일

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Fan Xia이 arXiv에 게시한 'Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Language Models #Code Generation #Non-Autoregressive Inference #High-Speed Inference #Discrete Diffusion #LLM Inference

2025년 8월 6일

[논문리뷰] Multi-human Interactive Talking Dataset

Mike Zheng Shou이 arXiv에 게시한 'Multi-human Interactive Talking Dataset' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-human Video Generation #Interactive Talking #Dataset #Audio-driven Animation #Pose Control #Speech Interaction #Diffusion Models

2025년 8월 6일

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

Chenyang Si이 arXiv에 게시한 'LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Ultra-long Video Generation #Multimodal Guidance #Controllable Video Generation #Diffusion Models #Temporal Consistency #Visual Quality #Autoregressive Generation #Degradation-aware Training

2025년 8월 6일

[논문리뷰] LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

Shunyu Yao이 arXiv에 게시한 'LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Image Composition #Layout Control #Diffusion Models #Transformer #Attention Mechanisms #Training-Free #Zero-Shot Generalization

2025년 8월 6일

[논문리뷰] SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation

Long Chen이 arXiv에 게시한 'SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-driven Video Generation #Spatial Auditory Cues #Video Scene Layout #MLLM #Diffusion Models #Training-free

2025년 8월 4일

[논문리뷰] PixNerd: Pixel Neural Field Diffusion

Limin Wang이 arXiv에 게시한 'PixNerd: Pixel Neural Field Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Neural Fields #Pixel Space #Generative Models #Image Synthesis #Transformer Architecture #End-to-End Learning

2025년 8월 4일

[논문리뷰] villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Kaixin Wang이 arXiv에 게시한 'villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Latent Actions #Robot Manipulation #Pre-training #Diffusion Models #Proprioceptive Feedback #Foundation Models

2025년 8월 2일