Review

[논문리뷰] VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks

arXiv에 게시된 'VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #GUI Grounding #Multi-Platform #Benchmark #MLLM #Hierarchical Evaluation #Human-in-the-Loop Annotation #GUI Agents #Multilingual Dataset

2025년 12월 18일

[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] Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

arXiv에 게시된 'Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model' 논문에 대한 자세한 리뷰입니다.

#Review #Audio-Visual Generation #Diffusion Transformer #Multimodal AI #Speech Synchronization #Video Generation #Reinforcement Learning from Human Feedback #Inference Acceleration

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] REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion

Giorgos Sfikas이 arXiv에 게시한 'REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Latent Diffusion Models #Vision Foundation Models #Semantic Compression #Global-Local Semantics #Image Generation #Representation Entanglement #Transformer Architecture

2025년 12월 18일

[논문리뷰] Next-Embedding Prediction Makes Strong Vision Learners

arXiv에 게시된 'Next-Embedding Prediction Makes Strong Vision Learners' 논문에 대한 자세한 리뷰입니다.

#Review #Self-supervised Learning #Generative Pretraining #Vision Transformer #Next-Embedding Prediction #Autoregressive Model #Image Classification #Semantic Segmentation #Causal Masking

2025년 12월 18일

[논문리뷰] N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

arXiv에 게시된 'N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #3D Grounding #Spatial Reasoning #Vision-Language Models #Depth Estimation #3D Object Detection #Chain-of-Thought #Data Generation #Multimodal AI

2025년 12월 18일

[논문리뷰] Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image

arXiv에 게시된 'Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image' 논문에 대한 자세한 리뷰입니다.

#Review #Reward Models #Multimodal LLMs #Benchmark #Text-to-Image Generation #Image Editing #Interleaved Generation #Multimodal Reasoning #MLLM-as-a-judge

2025년 12월 18일

[논문리뷰] Kling-Omni Technical Report

arXiv에 게시된 'Kling-Omni Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multimodal Visual Language #Generative AI #Video Editing #Reasoning-enhanced Generation #Diffusion Transformer #Multi-modal World Simulators

2025년 12월 18일

[논문리뷰] Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

arXiv에 게시된 'Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language' 논문에 대한 자세한 리뷰입니다.

#Review #Time Series Analysis #Multimodal Language Models #Natural Language Generation #Dataset Creation #Instruction Tuning #GPT-4 #LLaVA #Cross-Domain Alignment

2025년 12월 18일

[논문리뷰] Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

Carlos Escolano이 arXiv에 게시한 'Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Speech-to-Text Translation #Multimodal LLMs #Speech Foundation Models #Cascaded Systems #Benchmarking #Speech Modality Integration #Robustness #Evaluation Metrics

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] Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

arXiv에 게시된 'Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Exploration-Exploitation #Clipping #Policy Entropy #Spurious Rewards #Mathematical Reasoning #RLVR

2025년 12월 18일

[논문리뷰] Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification

arXiv에 게시된 'Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification' 논문에 대한 자세한 리뷰입니다.

#Review #MLLM #Model Auditing #Capability Gaps #Failure Mode Discovery #Reinforcement Learning #Data Rectification #Counterfactual Generation #VQA

2025년 12월 18일

[논문리뷰] Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation

Wenxuan Lu이 arXiv에 게시한 'Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation' 논문에 대한 자세한 리뷰입니다.

#Review #Panoramic Depth Estimation #Foundation Model #Semi-Supervised Learning #Pseudo-Labeling #Data-in-the-Loop #DINOv3 #Metric Depth #360-degree Vision

2025년 12월 18일

[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] Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection

Jiarong Ou이 arXiv에 게시한 'Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image #Data Selection #Meta-Learning #Meta-Gradient #Data Efficiency #Generative Models #Coreset Selection #Data Pruning

2025년 12월 18일