[논문리뷰] CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text RecognitionarXiv에 게시된 'CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition' 논문에 대한 자세한 리뷰입니다.#Review#Historical Text Recognition#Vision-Language Model#Open-Weight Model#OCR#Cultural Heritage#Low-Cost AI#Dataset Curation#Fine-tuning2025년 9월 29일댓글 수 로딩 중
[논문리뷰] When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine ValidityJohn P Dickerson이 arXiv에 게시한 'When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity' 논문에 대한 자세한 리뷰입니다.#Review#LLM Judge#Benchmark Evaluation#Validity#Reliability#Psychometrics#Factor Analysis#Schema Adherence#ELO Ranking2025년 9월 26일댓글 수 로딩 중
[논문리뷰] VCRL: Variance-based Curriculum Reinforcement Learning for Large Language ModelsYuewei Zhang이 arXiv에 게시한 'VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Curriculum Learning#Large Language Models#Mathematical Reasoning#Variance-based Sampling#Replay Learning#Policy Optimization2025년 9월 26일댓글 수 로딩 중
[논문리뷰] V-GameGym: Visual Game Generation for Code Large Language ModelsShawn Guo이 arXiv에 게시한 'V-GameGym: Visual Game Generation for Code Large Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Code Large Language Models#Visual Game Generation#Benchmark#Pygame#Multimodal Evaluation#Software Engineering#AI-assisted Game Development2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode TheoryYanbin Fu이 arXiv에 게시한 'Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory' 논문에 대한 자세한 리뷰입니다.#Review#Large Reasoning Models#Cognitive Science#Schoenfeld's Episode Theory#Math Problem Solving#Chain-of-Thought#Behavioral Analysis#Dataset Annotation2025년 9월 26일댓글 수 로딩 중
[논문리뷰] TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate ThemZhuohao Yu이 arXiv에 게시한 'TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them' 논문에 대한 자세한 리뷰입니다.#Review#LLM-as-a-Judge#Evaluation Frameworks#Inconsistency Reduction#Probabilistic Scoring#Transitivity#Information Loss#Perplexity#Large Language Models2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Tree Search for LLM Agent Reinforcement LearningXiangxiang Chu이 arXiv에 게시한 'Tree Search for LLM Agent Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#LLM Agents#Reinforcement Learning#Tree Search#Policy Optimization#Preference Learning#Sparse Rewards#Multi-turn Tasks2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Thinking While Listening: Simple Test Time Scaling For Audio ClassificationMert Pilanci이 arXiv에 게시한 'Thinking While Listening: Simple Test Time Scaling For Audio Classification' 논문에 대한 자세한 리뷰입니다.#Review#Audio Classification#Test-Time Scaling#Reasoning Traces#Large Language Models (LLMs)#Transformer Architectures#Zero-shot Reasoning#Computational Efficiency2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Thinking Augmented Pre-trainingFuru Wei이 arXiv에 게시한 'Thinking Augmented Pre-training' 논문에 대한 자세한 리뷰입니다.#Review#Large Language Models (LLMs)#Pre-training#Data Augmentation#Reasoning#Data Efficiency#Thinking Trajectories2025년 9월 26일댓글 수 로딩 중
[논문리뷰] The Unanticipated Asymmetry Between Perceptual Optimization and AssessmentDu Chen이 arXiv에 게시한 'The Unanticipated Asymmetry Between Perceptual Optimization and Assessment' 논문에 대한 자세한 리뷰입니다.#Review#Perceptual Optimization#Image Quality Assessment (IQA)#Adversarial Training#Discriminators#Super-Resolution#Fidelity Metrics#Deep Learning2025년 9월 26일댓글 수 로딩 중
[논문리뷰] StyleBench: Evaluating thinking styles in Large Language ModelsJavad Lavaei이 arXiv에 게시한 'StyleBench: Evaluating thinking styles in Large Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Large Language Models#Reasoning Strategies#Prompt Engineering#LLM Evaluation#Benchmark#Thinking Styles#Scaling Laws#Meta-Reasoning2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Seedream 4.0: Toward Next-generation Multimodal Image GenerationYunpeng Chen이 arXiv에 게시한 'Seedream 4.0: Toward Next-generation Multimodal Image Generation' 논문에 대한 자세한 리뷰입니다.#Review#Multimodal Image Generation#Diffusion Transformer#VAE#Image Editing#Text-to-Image#Model Acceleration#Human Evaluation2025년 9월 26일댓글 수 로딩 중
[논문리뷰] SciReasoner: Laying the Scientific Reasoning Ground Across DisciplinesJiabei Xiao이 arXiv에 게시한 'SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines' 논문에 대한 자세한 리뷰입니다.#Review#Scientific Reasoning#Foundation Models#Multi-modal Learning#Cross-domain Generalization#Chain-of-Thought#Reinforcement Learning#Scientific Discovery#Molecular Design2025년 9월 26일댓글 수 로딩 중
[논문리뷰] SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective AgentSiyuan Huang이 arXiv에 게시한 'SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent' 논문에 대한 자세한 리뷰입니다.#Review#3D Scene Synthesis#Agentic Framework#LLMs#Self-Reflection#Tool-Use#Physical Plausibility#Iterative Refinement#Embodied AI2025년 9월 26일댓글 수 로딩 중
[논문리뷰] ScaleDiff: Scaling Difficult Problems for Advanced Mathematical ReasoningYu Li이 arXiv에 게시한 'ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning' 논문에 대한 자세한 리뷰입니다.#Review#Mathematical Reasoning#Large Reasoning Models (LRMs)#Difficulty Scaling#Data Augmentation#Supervised Fine-Tuning (SFT)#Problem Generation#Solution Distillation2025년 9월 26일댓글 수 로딩 중
[논문리뷰] SD3.5-Flash: Distribution-Guided Distillation of Generative FlowsYi-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 Alignment2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Residual Off-Policy RL for Finetuning Behavior Cloning PoliciesPieter Abbeel이 arXiv에 게시한 'Residual Off-Policy RL for Finetuning Behavior Cloning Policies' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning (RL)#Behavior Cloning (BC)#Residual Learning#Off-Policy RL#Robot Manipulation#Real-World Robotics#High-DoF Systems#Sample Efficiency2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task ExecutionJinjie Gu이 arXiv에 게시한 'Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution' 논문에 대한 자세한 리뷰입니다.#Review#Multi-Agent System#Browser Automation#Web Reconnaissance#Tool Generation#Task Execution#Self-Evolving AI#LLM/VLM#VisualWebArena2025년 9월 26일댓글 수 로딩 중
[논문리뷰] Quantized Visual Geometry Grounded TransformerYuqi Li이 arXiv에 게시한 'Quantized Visual Geometry Grounded Transformer' 논문에 대한 자세한 리뷰입니다.#Review#Quantization#Post-Training Quantization#3D Reconstruction#Visual Transformer#Model Compression#Efficient Inference#Hadamard Rotation#Calibration Sampling2025년 9월 26일댓글 수 로딩 중
[논문리뷰] MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal ReasoningJunyan Zhang이 arXiv에 게시한 'MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning' 논문에 대한 자세한 리뷰입니다.#Review#Video Temporal Reasoning#Reinforcement Learning#Process Supervision#Dynamic Time Warping#Multimodal Large Language Models#Video State Prediction#Reward Hacking2025년 9월 26일댓글 수 로딩 중