#Diffusion Transformers

31개의 포스트

[논문리뷰] On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

arXiv에 게시된 'On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Generative Diversity #Contextual Space #Repulsion Mechanism #Multi-modal Attention #Typicality Bias #Token Intervention

2026년 3월 30일

[논문리뷰] WorldCache: Content-Aware Caching for Accelerated Video World Models

Salman Khan이 arXiv에 게시한 'WorldCache: Content-Aware Caching for Accelerated Video World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Video World Models #Feature Caching #Inference Acceleration #Content-Aware Caching #Motion-Adaptive Caching #Perception-Constrained Caching #Optimal Feature Approximation

2026년 3월 23일

[논문리뷰] WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

arXiv에 게시된 'WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation' 논문에 대한 자세한 리뷰입니다.

#Review #Interactive Gaming World Models #Camera Pose #Geometric Representation #Diffusion Transformers #Action Control #3D Consistency #Lie Algebra

2026년 3월 17일

[논문리뷰] WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation

arXiv에 게시된 'WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation' 논문에 대한 자세한 리뷰입니다.

#Review #Image Generation #Flow Matching #Trajectory Conflict #Diffusion Transformers #Waypoint Diffusion Transformers #Just-Pixel AdaLN

2026년 3월 17일

[논문리뷰] Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers

Zhaoqiang Liu이 arXiv에 게시한 'Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Spatial Acceleration #Training-Free #Generative AI #Flow Matching #ODE Solvers #Inference Speedup #Resource Allocation

2026년 3월 11일

[논문리뷰] Helios: Real Real-Time Long Video Generation Model

arXiv에 게시된 'Helios: Real Real-Time Long Video Generation Model' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Real-Time #Long Video #Diffusion Transformers #Anti-Drifting #Memory Optimization #Distillation #Autoregressive Models

2026년 3월 4일

[논문리뷰] DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Deepti Ghadiyaram이 arXiv에 게시한 'DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Dynamic Tokenization #Patch Scheduling #Inference Acceleration #Text-to-Image Generation #Text-to-Video Generation #Latent Manifold Analysis #LoRA

2026년 2월 19일

[논문리뷰] ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

arXiv에 게시된 'ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Robotic Manipulation #Vision-Language-Action (VLA)#Foundation Models #Action Manifold Learning #Diffusion Transformers #Data Curation #Embodied AI

2026년 2월 15일

[논문리뷰] Rethinking Global Text Conditioning in Diffusion Transformers

Yuchen Liu이 arXiv에 게시한 'Rethinking Global Text Conditioning in Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Text Conditioning #CLIP Embedding #Modulation Guidance #Text-to-Image Generation #Image Editing #Training-free

2026년 2월 10일

[논문리뷰] 360Anything: Geometry-Free Lifting of Images and Videos to 360°

arXiv에 게시된 '360Anything: Geometry-Free Lifting of Images and Videos to 360°' 논문에 대한 자세한 리뷰입니다.

#Review #Panorama Generation #Diffusion Transformers #Geometry-Free Learning #Latent Encoding #Seam Artifacts #Camera Pose Estimation #Video Outpainting

2026년 1월 22일

[논문리뷰] SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

arXiv에 게시된 'SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Edge AI #Efficient Image Generation #Sparse Attention #Elastic Training #Knowledge Distillation #Mobile AI #High-Fidelity

2026년 1월 13일

[논문리뷰] SAM Audio: Segment Anything in Audio

arXiv에 게시된 'SAM Audio: Segment Anything in Audio' 논문에 대한 자세한 리뷰입니다.

#Review #Audio Source Separation #Foundation Models #Multimodal Prompting #Diffusion Transformers #Flow Matching #Self-Supervised Learning #Reference-Free Evaluation #Audio-Visual Learning

2025년 12월 23일

[논문리뷰] DeContext as Defense: Safe Image Editing in Diffusion Transformers

arXiv에 게시된 'DeContext as Defense: Safe Image Editing in Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Image Editing #Privacy Protection #Adversarial Attack #Attention Mechanism #Identity Preservation #Deepfake Defense #In-context Learning

2025년 12월 18일

[논문리뷰] IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

arXiv에 게시된 'IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Video VFX Editing #In-Context Learning #Diffusion Transformers #Few-Shot Learning #LoRA #Spatiotemporal Tokenization #Instruction-Guided

2025년 12월 17일

[논문리뷰] UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers

arXiv에 게시된 'UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Resolution Extrapolation #Positional Encoding #Frequency Analysis #Adaptive Attention #High-Resolution Image Generation #Image Quality #Content Repetition

2025년 12월 4일

[논문리뷰] REASONEDIT: Towards Reasoning-Enhanced Image Editing Models

arXiv에 게시된 'REASONEDIT: Towards Reasoning-Enhanced Image Editing Models' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Reasoning-Enhanced AI #Multimodal Large Language Models #Diffusion Transformers #Thinking #Reflection #Iterative Refinement #Instruction Following

2025년 11월 30일

[논문리뷰] OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation

arXiv에 게시된 'OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation' 논문에 대한 자세한 리뷰입니다.

#Review #RGBA Generation #Multi-Task Learning #Diffusion Transformers #Image Matting #Layer Decomposition #Object Removal #Alpha-aware VAE #MSROPE-BiL

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] LiteAttention: A Temporal Sparse Attention for Diffusion Transformers

arXiv에 게시된 'LiteAttention: A Temporal Sparse Attention for Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Sparse Attention #Temporal Coherence #Video Generation #Computational Efficiency #FlashAttention #CUDA Kernels

2025년 11월 16일

[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] Group Relative Attention Guidance for Image Editing

arXiv에 게시된 'Group Relative Attention Guidance for Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Transformers #Attention Mechanism #Guidance Mechanism #Controllability #Fine-grained Control #GRAG

2025년 10월 29일

[논문리뷰] Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

Honglie Chen이 arXiv에 게시한 'Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-driven Animation #Identity Preservation #Diffusion Transformers #Long-form Video Generation #Temporal Autoregression #Keyframe Anchoring #Self-keyframing

2025년 10월 28일

[논문리뷰] Video-As-Prompt: Unified Semantic Control for Video Generation

arXiv에 게시된 'Video-As-Prompt: Unified Semantic Control for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Semantic Control #Diffusion Transformers #In-Context Learning #Mixture-of-Transformers #Video-As-Prompt #Controllable Generation #Large-scale Dataset

2025년 10월 27일

[논문리뷰] MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation

arXiv에 게시된 'MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Long Video Generation #Sparse Attention #Diffusion Transformers #Mixture-of-Groups Attention #Token Routing #Computational Efficiency #Context Length

2025년 10월 22일

[논문리뷰] MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Hyunwook Choi이 arXiv에 게시한 'MATRIX: Mask Track Alignment for Interaction-aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Transformers #Human-Object Interaction #Attention Alignment #Mask Tracking #Semantic Grounding #Semantic Propagation #Text-to-Video

2025년 10월 9일

[논문리뷰] SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

arXiv에 게시된 'SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Transformers #Sparse Attention #Linear Attention #Model Acceleration #Video Generation #Attention Mechanisms #Fine-tuning

2025년 9월 30일

[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] ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

Yue Ma이 arXiv에 게시한 'ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment' 논문에 대한 자세한 리뷰입니다.

#Review #Video Object Editing #Training-Free #Diffusion Transformers #Rectified Flow #Adaptive Context Enrichment #Guidance Responsiveness #Temporal Consistency #Image-to-Video

2025년 9월 23일

[논문리뷰] EgoTwin: Dreaming Body and View in First Person

Wentao Wang이 arXiv에 게시한 'EgoTwin: Dreaming Body and View in First Person' 논문에 대한 자세한 리뷰입니다.

#Review #Egocentric Video Generation #Human Motion Synthesis #Diffusion Transformers #Multimodal Generation #Viewpoint Alignment #Causal Interplay #First-Person Vision

2025년 8월 25일

[논문리뷰] Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Deyu Zhou이 arXiv에 게시한 'Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer' 논문에 대한 자세한 리뷰입니다.

#Review #Text-Guided Editing #Color Editing #Diffusion Transformers #Training-Free #Multi-Modal AI #Attention Control #Image Manipulation

2025년 8월 20일

[논문리뷰] DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

Chao Liang이 arXiv에 게시한 'DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework' 논문에 대한 자세한 리뷰입니다.

#Review #Video Virtual Try-On #Diffusion Transformers #Stage-Wise Framework #Vision-Language Models #LoRA #Temporal Consistency #Garment Preservation

2025년 8월 7일