Review

[논문리뷰] AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

arXiv에 게시된 'AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Benchmark #Cultural Understanding #Contextual Inference #Audio-Visual Memes #Multilingual #Q&A Evaluation

2026년 1월 27일

[논문리뷰] A Pragmatic VLA Foundation Model

arXiv에 게시된 'A Pragmatic VLA Foundation Model' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Model #Robotics #Foundation Models #Multi-Embodiment Learning #Data Scaling #Computational Efficiency #Real-world Deployment

2026년 1월 27일

[논문리뷰] iFSQ: Improving FSQ for Image Generation with 1 Line of Code

arXiv에 게시된 'iFSQ: Improving FSQ for Image Generation with 1 Line of Code' 논문에 대한 자세한 리뷰입니다.

#Review #Finite Scalar Quantization (FSQ)#Image Generation #Autoregressive Models #Diffusion Models #Quantization #Tokenization #Representation Alignment (REPA)#Latent Space

2026년 1월 26일

[논문리뷰] daVinci-Dev: Agent-native Mid-training for Software Engineering

arXiv에 게시된 'daVinci-Dev: Agent-native Mid-training for Software Engineering' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Software Engineering #Mid-training #Large Language Models #Agent-native Data #Contextual Trajectories #Environmental Trajectories #SWE-Bench Verified #Code Generation

2026년 1월 26일

[논문리뷰] VIBEVOICE-ASR Technical Report

arXiv에 게시된 'VIBEVOICE-ASR Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Automatic Speech Recognition #Speaker Diarization #Long-form Audio #Large Language Models #End-to-end Speech Processing #Multilingual #Context-aware ASR

2026년 1월 26일

[논문리뷰] The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

arXiv에 게시된 'The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Dialogue-to-Video Generation #Agentic AI #Cinematic Scripting #Long-Horizon Video Synthesis #Visual Coherence #Reinforcement Learning #Multimodal LLM

2026년 1월 26일

[논문리뷰] Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

arXiv에 게시된 'Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability' 논문에 대한 자세한 리뷰입니다.

#Review #Meta-RL #Curriculum Learning #Self-Play #LLM Reasoning #Sparse Rewards #Question Generation #Bilevel Optimization

2026년 1월 26일

[논문리뷰] SkyReels-V3 Technique Report

arXiv에 게시된 'SkyReels-V3 Technique Report' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multimodal AI #Diffusion Models #Transformer Architecture #Reference-guided Generation #Video-to-Video #Audio-driven Animation #Temporal Consistency

2026년 1월 26일

[논문리뷰] Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

arXiv에 게시된 'Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility' 논문에 대한 자세한 리뷰입니다.

#Review #Scientific Image Synthesis #Multimodal Reasoning #Text-to-Image #Benchmarking #Programmatic Synthesis #Large Multimodal Models #Synthetic Data

2026년 1월 26일

[논문리뷰] STAR: Semantic Table Representation with Header-Aware Clustering and Adaptive Weighted Fusion

arXiv에 게시된 'STAR: Semantic Table Representation with Header-Aware Clustering and Adaptive Weighted Fusion' 논문에 대한 자세한 리뷰입니다.

#Review #Table Retrieval #Semantic Representation #K-means Clustering #Weighted Fusion #Large Language Models #Query Generation #Information Retrieval

2026년 1월 26일

[논문리뷰] SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback

arXiv에 게시된 'SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback' 논문에 대한 자세한 리뷰입니다.

#Review #Deep Search #Agentic Data Generation #LLMs #Execution Feedback #Reinforcement Learning #Question Answering #Synthetic Data

2026년 1월 26일

[논문리뷰] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents

arXiv에 게시된 'Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Reinforcement Learning #Cross-Domain Generalization #State Information Richness #Planning Complexity #State Augmentation #Step-by-Step Reasoning #Mid-Training

2026년 1월 26일

[논문리뷰] Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models

Guanhong Tao이 arXiv에 게시한 'Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #LVLM Security #Token Compression #Adversarial Attack #Robustness Degradation #Compression-Aware Attack #Efficiency-Security Trade-off #Black-box Attack

2026년 1월 26일

[논문리뷰] End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions

Shrikanth Narayanan이 arXiv에 게시한 'End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions' 논문에 대한 자세한 리뷰입니다.

#Review #End-to-End ASR #Speaker Diarization #Child Speech Processing #Whisper Model #Serialized Output Training #Multi-task Learning #State-Machine Decoding

2026년 1월 26일

[논문리뷰] Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

arXiv에 게시된 'Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Transformer #Sparse Attention #Adaptive Sparsity #Efficient LLM #Attention Router #Long-Context #Hybrid Attention

2026년 1월 26일

[논문리뷰] DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

arXiv에 게시된 'DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Long-Horizon Planning #Benchmarking #Verifiable Constraints #Tool Use #Constraint Optimization #Information Acquisition #Travel Planning #Shopping Planning

2026년 1월 26일

[논문리뷰] DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Jiaxuan You이 arXiv에 게시한 'DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal' 논문에 대한 자세한 리뷰입니다.

#Review #Academic Rebuttal #LLM Agents #Peer Review Automation #Generative AI #Retrieval-Augmented Generation (RAG)#Strategic Planning #Persuasion

2026년 1월 26일

[논문리뷰] Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

arXiv에 게시된 'Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Data Preparation #LLMs #Data Cleaning #Data Integration #Data Enrichment #AI Agents #Semantic Reasoning #Workflow Automation

2026년 1월 26일

[논문리뷰] CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval

arXiv에 게시된 'CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval' 논문에 대한 자세한 리뷰입니다.

#Review #Table Retrieval #LLM Supervision #K-means Clustering #Partial Table #Contrastive Learning #Embedding Fine-tuning #Synthetic Query Generation

2026년 1월 26일

[논문리뷰] Agentic Very Long Video Understanding

arXiv에 게시된 'Agentic Very Long Video Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Horizon Video Understanding #Agentic AI #Entity Graph #Multimodal Reasoning #Video Question Answering #EgoLifeQA #Retrieval Augmented Generation

2026년 1월 26일