[논문리뷰] DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent SystemsarXiv에 게시된 'DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems' 논문에 대한 자세한 리뷰입니다.#Review#LLM Multi-Agent Systems#Debugging#Intervention-Driven#Failure Attribution#Automated Debugging#Verification#AI Agents#Reliability2025년 12월 8일댓글 수 로딩 중
[논문리뷰] Distribution Matching Variational AutoEncoderarXiv에 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#Tokenizer2025년 12월 8일댓글 수 로딩 중
[논문리뷰] Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language ReasoningarXiv에 게시된 'Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning' 논문에 대한 자세한 리뷰입니다.#Review#Vision-Language Models#Reinforcement Learning#Self-Evolving Learning#Data-Scarce Domains#Context-First Learning#Reward Hacking Mitigation#Multimodal Reasoning#Curriculum Learning2025년 12월 8일댓글 수 로딩 중
[논문리뷰] DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context DialogueYijunLiao이 arXiv에 게시한 'DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue' 논문에 대한 자세한 리뷰입니다.#Review#Long-Context Dialogue#Mutable State Tracking#Temporal Alignment#Preference Optimization#Attention Mechanism#State Inertia#Non-Destructive Alignment2025년 12월 8일댓글 수 로딩 중
[논문리뷰] Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement LearningJiacheng Chen이 arXiv에 게시한 'Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#Decoding-based Regression#Reinforcement Learning#Numerical Prediction#Large Language Models#Policy Gradient#Tokenization#Sequence Generation2025년 12월 8일댓글 수 로딩 중
[논문리뷰] Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMsarXiv에 게시된 'Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs' 논문에 대한 자세한 리뷰입니다.#Review#Rotary Position Embedding#Long-Context LLMs#Complex-Valued Neural Networks#Self-Attention#Positional Encoding#Information Loss#Length Extrapolation2025년 12월 8일댓글 수 로딩 중
[논문리뷰] World Models That Know When They Don't Know: Controllable Video Generation with Calibrated UncertaintyAnirudha Majumdar이 arXiv에 게시한 'World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty' 논문에 대한 자세한 리뷰입니다.#Review#Controllable Video Generation#Uncertainty Quantification#Video Models#Calibration#Out-of-Distribution Detection#Proper Scoring Rules#Latent Space2025년 12월 7일댓글 수 로딩 중
[논문리뷰] TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial FlowsarXiv에 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 Models2025년 12월 7일댓글 수 로딩 중
[논문리뷰] TimesNet-Gen: Deep Learning-based Site Specific Strong Motion GenerationSalih Tileylioglu이 arXiv에 게시한 'TimesNet-Gen: Deep Learning-based Site Specific Strong Motion Generation' 논문에 대한 자세한 리뷰입니다.#Review#Strong Motion Generation#Deep Learning#TimesNet#Conditional Generation#Site Effects#Seismology#HVSR#Time Series2025년 12월 7일댓글 수 로딩 중
[논문리뷰] SpaceControl: Introducing Test-Time Spatial Control to 3D Generative ModelingMarc Pollefeys이 arXiv에 게시한 'SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling' 논문에 대한 자세한 리뷰입니다.#Review#3D Generative Models#Spatial Control#Test-Time Guidance#Rectified Flow#Superquadrics#Training-Free#Trellis2025년 12월 7일댓글 수 로딩 중
[논문리뷰] Self-Improving VLM Judges Without Human AnnotationsarXiv에 게시된 'Self-Improving VLM Judges Without Human Annotations' 논문에 대한 자세한 리뷰입니다.#Review#Vision-Language Models#Self-Improvement#Judge Models#Synthetic Data Generation#Iterative Refinement#Reward Modeling#Human-free Alignment2025년 12월 7일댓글 수 로딩 중
[논문리뷰] SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMsMinghui Yu이 arXiv에 게시한 'SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs' 논문에 대한 자세한 리뷰입니다.#Review#LLM Quantization#Sparsification#Hardware Acceleration#Mixed-Precision#Post-Training Quantization#Data Format#GPU Optimization#AI Accelerator2025년 12월 7일댓글 수 로딩 중
[논문리뷰] SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose RepresentationsarXiv에 게시된 'SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations' 논문에 대한 자세한 리뷰입니다.#Review#Character Animation#3D Pose Representation#In-Context Learning#Diffusion Transformer#Studio-Grade Animation#Spatio-Temporal Reasoning#Video Generation2025년 12월 7일댓글 수 로딩 중
[논문리뷰] RealGen: Photorealistic Text-to-Image Generation via Detector-Guided RewardsZilong 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 Assessment2025년 12월 7일댓글 수 로딩 중
[논문리뷰] ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement LearningShengju Qian이 arXiv에 게시한 'ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#Video Object Segmentation#Reinforcement Learning#Vision-Language Models#Reasoning Chain#Explainable AI#Multi-step Reasoning2025년 12월 7일댓글 수 로딩 중
[논문리뷰] ProPhy: Progressive Physical Alignment for Dynamic World SimulationYuhao Cheng이 arXiv에 게시한 'ProPhy: Progressive Physical Alignment for Dynamic World Simulation' 논문에 대한 자세한 리뷰입니다.#Review#Video Generation#Physics-aware#World Simulation#Progressive Alignment#Mixture-of-Experts#Vision-Language Models#Token-level Routing2025년 12월 7일댓글 수 로딩 중
[논문리뷰] Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single ImagearXiv에 게시된 'Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image' 논문에 대한 자세한 리뷰입니다.#Review#4D Synthesis#3D Reconstruction#Motion Generation#Single Image#Diffusion Model#Point Cloud#Dataset Curation#View Synthesis2025년 12월 7일댓글 수 로딩 중
[논문리뷰] From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning TasksYang Li이 arXiv에 게시한 'From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Large Language Models#Curriculum Learning#Advantage Function#Reasoning Tasks#Multimodal AI#Policy Optimization#Generalization2025년 12월 7일댓글 수 로딩 중
[논문리뷰] Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement LearningZijia Lin이 arXiv에 게시한 'Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Policy Optimization#Trust Region#Entropy Clipping#Large Language Models#Training Stability#Distributional Shift2025년 12월 7일댓글 수 로딩 중
[논문리뷰] EditThinker: Unlocking Iterative Reasoning for Any Image EditorZiyu Guo이 arXiv에 게시한 'EditThinker: Unlocking Iterative Reasoning for Any Image Editor' 논문에 대한 자세한 리뷰입니다.#Review#Image Editing#Iterative Reasoning#Multimodal Large Language Model (MLLM)#Reinforcement Learning (RL)#Instruction Following#Critique-Refine-Repeat Cycle#Think-while-Edit2025년 12월 7일댓글 수 로딩 중