[논문리뷰] First Try Matters: Revisiting the Role of Reflection in Reasoning ModelsWee Sun Lee이 arXiv에 게시한 'First Try Matters: Revisiting the Role of Reflection in Reasoning Models' 논문에 대한 자세한 리뷰입니다.#Review#Large Language Models (LLMs)#Reasoning#Chain-of-Thought (CoT)#Reflection#Early Stopping#Supervised Fine-tuning (SFT)#Token Efficiency#Mathematical Reasoning2025년 10월 10일댓글 수 로딩 중
[논문리뷰] Fidelity-Aware Data Composition for Robust Robot GeneralizationLiliang 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 Synthesis2025년 10월 10일댓글 수 로딩 중
[논문리뷰] Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy ConstraintsHuazhe Xu이 arXiv에 게시한 'Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints' 논문에 대한 자세한 리뷰입니다.#Review#Entropy Regularization#Activation Functions#Continuous Control#Large Language Models#Image Classification#Reinforcement Learning#Policy Stochasticity#Entropy Constraints2025년 10월 10일댓글 수 로딩 중
[논문리뷰] DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics ModelLi Yi이 arXiv에 게시한 'DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model' 논문에 대한 자세한 리뷰입니다.#Review#Dexterous Manipulation#In-Hand Rotation#Sim-to-Real Transfer#Neural Dynamics Model#Joint-Wise Learning#Autonomous Data Collection#Reinforcement Learning#Robotics2025년 10월 10일댓글 수 로딩 중
[논문리뷰] DeepPrune: Parallel Scaling without Inter-trace RedundancyarXiv에 게시된 'DeepPrune: Parallel Scaling without Inter-trace Redundancy' 논문에 대한 자세한 리뷰입니다.#Review#Parallel Scaling#Chain-of-Thought#LLM Reasoning#Dynamic Pruning#Inter-trace Redundancy#Judge Model#Resource Efficiency#Answer Diversity2025년 10월 10일댓글 수 로딩 중
[논문리뷰] CoMAS: Co-Evolving Multi-Agent Systems via Interaction RewardsYijiang Li이 arXiv에 게시한 'CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards' 논문에 대한 자세한 리뷰입니다.#Review#Multi-Agent Systems#LLM Agents#Self-Evolution#Reinforcement Learning#Interaction Rewards#LLM-as-a-Judge#Decentralized Learning2025년 10월 10일댓글 수 로딩 중
[논문리뷰] Beyond Turn Limits: Training Deep Search Agents with Dynamic Context WindowYaojie Lu이 arXiv에 게시한 'Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window' 논문에 대한 자세한 리뷰입니다.#Review#Deep Search Agents#Dynamic Context Window#Reinforcement Learning#Long-horizon Interaction#Context Management#High-difficulty Tasks#Multi-turn Reasoning#Web Agents2025년 10월 10일댓글 수 로딩 중
[논문리뷰] Beyond Outliers: A Study of Optimizers Under QuantizationarXiv에 게시된 'Beyond Outliers: A Study of Optimizers Under Quantization' 논문에 대한 자세한 리뷰입니다.#Review#Quantization#Optimizers#LLM#Post-Training Quantization (PTQ)#Quantization-Aware Training (QAT)#Error Propagation#Scaling Laws#Shampoo2025년 10월 10일댓글 수 로딩 중
[논문리뷰] Agent Learning via Early ExperiencearXiv에 게시된 'Agent Learning via Early Experience' 논문에 대한 자세한 리뷰입니다.#Review#Language Agents#Early Experience#Reward-Free Learning#World Modeling#Self-Reflection#Imitation Learning#Reinforcement Learning#Out-of-Domain Generalization2025년 10월 10일댓글 수 로딩 중
[논문리뷰] ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene RepresentationarXiv에 게시된 'ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation' 논문에 대한 자세한 리뷰입니다.#Review#3D Reconstruction#Monocular SLAM#Gaussian Splatting#Level of Detail (LoD)#Feed-Forward Models#Structured Scene Representation#Real-time#High-Fidelity2025년 10월 10일댓글 수 로딩 중
[논문리뷰] A^2Search: Ambiguity-Aware Question Answering with Reinforcement LearningarXiv에 게시된 'A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#Question Answering#Reinforcement Learning#Large Language Models#Ambiguity Resolution#Multi-hop QA#Automated Data Generation#Tool-Augmented LLMs#AnsF1 Reward2025년 10월 10일댓글 수 로딩 중
[논문리뷰] WristWorld: Generating Wrist-Views via 4D World Models for Robotic ManipulationarXiv에 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-View2025년 10월 9일댓글 수 로딩 중
[논문리뷰] Why Low-Precision Transformer Training Fails: An Analysis on Flash AttentionarXiv에 게시된 'Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention' 논문에 대한 자세한 리뷰입니다.#Review#Low-Precision Training#Flash Attention#Transformer#Numerical Stability#BF16#Rounding Error#Gradient Bias#Deep Learning Optimization2025년 10월 9일댓글 수 로딩 중
[논문리뷰] When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality EvaluationarXiv에 게시된 'When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation' 논문에 대한 자세한 리뷰입니다.#Review#LLM Factuality Evaluation#Benchmark Aging#Temporal Misalignment#Information Retrieval#Question Answering#Evaluation Metrics#GPT-4o-mini#Qwen2.52025년 10월 9일댓글 수 로딩 중
[논문리뷰] Vibe Checker: Aligning Code Evaluation with Human PreferencearXiv에 게시된 'Vibe Checker: Aligning Code Evaluation with Human Preference' 논문에 대한 자세한 리뷰입니다.#Review#Code Evaluation#Instruction Following#Human Preference#Large Language Models#Vibe Check#Non-functional Requirements#VeriCode2025년 10월 9일댓글 수 로딩 중
[논문리뷰] U-Bench: A Comprehensive Understanding of U-Net through 100-Variant BenchmarkingHeqin Zhu이 arXiv에 게시한 'U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking' 논문에 대한 자세한 리뷰입니다.#Review#U-Net#Medical Image Segmentation#Benchmarking#Performance Evaluation#Efficiency Metrics#Zero-shot Generalization#U-Score2025년 10월 9일댓글 수 로딩 중
[논문리뷰] The Markovian ThinkerarXiv에 게시된 'The Markovian Thinker' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Large Language Models#Chain-of-Thought#Markovian Thinking#Context Management#Computational Efficiency#Long-Context LLMs#Transformer Optimization2025년 10월 9일댓글 수 로딩 중
[논문리뷰] The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLParXiv에 게시된 'The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP' 논문에 대한 자세한 리뷰입니다.#Review#Low-Resource NLP#African Languages#Data Collection#Multilingual Models#Fine-Tuning#Speech Data#Text Data#Capacity Building2025년 10월 9일댓글 수 로딩 중
[논문리뷰] TTRV: Test-Time Reinforcement Learning for Vision Language ModelsSerena Yeung-Levy이 arXiv에 게시한 'TTRV: Test-Time Reinforcement Learning for Vision Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Vision-Language Models (VLMs)#Reinforcement Learning (RL)#Test-Time Adaptation#Unsupervised Learning#Image Recognition#Visual Question Answering (VQA)#Group Relative Policy Optimization (GRPO)#Entropy Regularization2025년 10월 9일댓글 수 로딩 중
[논문리뷰] StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State RepresentationarXiv에 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 Action2025년 10월 9일댓글 수 로딩 중