Review

[논문리뷰] Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization

Mahdi Ghaznavai이 arXiv에 게시한 'Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization' 논문에 대한 자세한 리뷰입니다.

#Review #Complexity OoD Generalization #System-1 Thinking #System-2 Reasoning #Kolmogorov Complexity #Inductive Biases #Large Language Models (LLMs)#Reasoning Evaluation

2025년 10월 13일

[논문리뷰] BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Hange Liu이 arXiv에 게시한 'BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution' 논문에 대한 자세한 리뷰입니다.

#Review #Code Generation #Human Preference #LLM Evaluation #Execution Feedback #Benchmarking #Crowdsourcing #Software Engineering #Large Language Models

2025년 10월 13일

[논문리뷰] Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models

arXiv에 게시된 'Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models' 논문에 대한 자세한 리뷰입니다.

#Review #Unpaired Multimodal Learning #Unimodal Representation #Weight Sharing #Cross-modal Transfer #Fisher Information #Self-supervised Learning #Multimodal Neurons #Data Efficiency

2025년 10월 13일

[논문리뷰] AutoPR: Let's Automate Your Academic Promotion!

Yixin Yuan이 arXiv에 게시한 'AutoPR: Let's Automate Your Academic Promotion!' 논문에 대한 자세한 리뷰입니다.

#Review #Academic Promotion #Large Language Models #Multi-Agent Systems #Scholarly Communication #Multimodal Processing #Benchmark #Content Generation #Social Media Marketing

2025년 10월 13일

[논문리뷰] Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Maksym Andriushchenko이 arXiv에 게시한 'Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols' 논문에 대한 자세한 리뷰입니다.

#Review #AI Control Protocols #LLM Monitors #Adaptive Attacks #Prompt Injection #Jailbreaking #Red Teaming #Scalable Oversight

2025년 10월 13일

[논문리뷰] ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping

Wenbo Hu이 arXiv에 게시한 'ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reasoning #Adaptive Learning #Reinforcement Learning #Entropy Shaping #Difficulty-Aware #Chain-of-Thought #Token-Level Analysis

2025년 10월 13일

[논문리뷰] ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

Jiaqi Tang이 arXiv에 게시한 'ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall' 논문에 대한 자세한 리뷰입니다.

#Review #Knowledge Editing #LLMs #Multi-hop Reasoning #Mechanistic Interpretability #Neuron-level Attribution #Factual Recall #Transformer Networks

2025년 10월 13일

[논문리뷰] A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

Fanchao Qi이 arXiv에 게시한 'A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Horizon Tasks #LLM Agents #Global Planning #Reinforcement Learning #Supervised Fine-tuning #Homologous Consensus Filtering #Executor Capability Gain Reward #Plan-and-Execute

2025년 10월 13일

[논문리뷰] When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs

arXiv에 게시된 'When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Context LMs #Multi-hop Reasoning #Thought Templates #Retrieval-Augmented Generation #Natural Language Feedback #Knowledge-intensive QA #Reasoning Reuse

2025년 10월 10일

[논문리뷰] VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

Quande Liu이 arXiv에 게시한 'VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Completion #Spatio-Temporal Control #In-Context Conditioning #Video Diffusion Models #RoPE Interpolation #VAE #Unified Framework #Video Generation

2025년 10월 10일

[논문리뷰] UniVideo: Unified Understanding, Generation, and Editing for Videos

Xintao Wang이 arXiv에 게시한 'UniVideo: Unified Understanding, Generation, and Editing for Videos' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Model #Video Generation #Video Editing #MLLM #Diffusion Transformer #In-Context Learning #Zero-shot Generalization #Multimodal AI

2025년 10월 10일

[논문리뷰] UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

arXiv에 게시된 'UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution' 논문에 대한 자세한 리뷰입니다.

#Review #Video Super-Resolution #Multi-Modal Generation #Latent Diffusion Models #Cascaded Framework #Condition Injection #Text-to-Video #Video Editing #4K Video

2025년 10월 10일

[논문리뷰] UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections

Boqian Li이 arXiv에 게시한 'UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections' 논문에 대한 자세한 리뷰입니다.

#Review #3D Human Reconstruction #Unconstrained Photos #Data Rectifier #Multi-View Generation #Pose-Correlated Feature Aggregation #SMPL-X #Diffusion Models #Virtual Try-On

2025년 10월 10일

[논문리뷰] UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

arXiv에 게시된 'UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal RAG #Document AI #Benchmark #Information Retrieval #Large Language Models #Multimodal Embeddings #PDF Processing #Question Answering

2025년 10월 10일

[논문리뷰] Training-Free Group Relative Policy Optimization

arXiv에 게시된 'Training-Free Group Relative Policy Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Reinforcement Learning #Parameter-Free Optimization #Experiential Knowledge #Token Prior #Group Relative Policy Optimization #In-Context Learning #Cost-Effective AI

2025년 10월 10일

[논문리뷰] Towards Scalable and Consistent 3D Editing

Pan Zhou이 arXiv에 게시한 'Towards Scalable and Consistent 3D Editing' 논문에 대한 자세한 리뷰입니다.

#Review #3D Editing #Generative Models #Transformer Architecture #Dataset Generation #Multimodal Learning #Conditional Generation #Image-to-3D

2025년 10월 10일

[논문리뷰] The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

arXiv에 게시된 'The Alignment Waltz: Jointly Training Agents to Collaborate for Safety' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Safety #Multi-agent Reinforcement Learning #Safety Alignment #Overrefusal #Adversarial Attacks #Feedback Agent #Conversation Agent #Dynamic Improvement Reward

2025년 10월 10일

[논문리뷰] Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction

arXiv에 게시된 'Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Sounding Video Generation #Diffusion Models #Dual-tower Architecture #Cross-modal Fusion #Visual Grounding #Hierarchical Captioning #Cross-Attention

2025년 10월 10일

[논문리뷰] Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models

James Cheng이 arXiv에 게시한 'Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Reinforcement Learning #Sentence Embedding #Retrieval-Augmented Generation #Chain-of-Thought #Information Retrieval #Supervised Fine-tuning

2025년 10월 10일

[논문리뷰] SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

Mohit Bansal이 arXiv에 게시한 'SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Reasoning #Multimodal AI #Scientific Research #Large Multimodal Models #Benchmark #Quantitative Reasoning #Domain Knowledge #Visual Grounding

2025년 10월 10일