Review

[논문리뷰] Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

arXiv에 게시된 'Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Kernel Generation #Triton #GPU Optimization #LLMs #Reward Hacking #Multi-turn Interaction #Code Generation

2026년 2월 5일

[논문리뷰] Context Forcing: Consistent Autoregressive Video Generation with Long Context

arXiv에 게시된 'Context Forcing: Consistent Autoregressive Video Generation with Long Context' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Autoregressive Models #Long Context #Temporal Consistency #Diffusion Models #Context Forcing #Memory Management #Distribution Matching Distillation

2026년 2월 5일

[논문리뷰] CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty

arXiv에 게시된 'CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Benchmarks #Tool-use #Consistency #Uncertainty Handling #Hallucination #In-car Assistant #Policy Adherence

2026년 2월 5일

[논문리뷰] Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation

Qintian Guo이 arXiv에 게시한 'Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Retrieval-Augmented Generation #Knowledge Graphs #Graph Traversal #Context-Aware Retrieval #Personalized PageRank #Multi-hop Reasoning #Semantic Drift Mitigation

2026년 2월 5일

[논문리뷰] BABE: Biology Arena BEnchmark

arXiv에 게시된 'BABE: Biology Arena BEnchmark' 논문에 대한 자세한 리뷰입니다.

#Review #Biology Benchmark #Large Language Models #Experimental Reasoning #Causal Inference #Cross-Scale Inference #Multimodal AI #Scientific Reasoning #Research Agents

2026년 2월 5일

[논문리뷰] WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

arXiv에 게시된 'WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent Reinforcement Learning #Width Scaling #Large Language Models #Information Seeking #Task Decomposition #Parallel Execution #Lead-Agent-Subagent Framework #Orchestration

2026년 2월 4일

[논문리뷰] Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration

arXiv에 게시된 'Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Content Generation #Orchestration #Vibe Coding #Meta-Planner #Human-in-the-Loop #Intent-Execution Gap

2026년 2월 4일

[논문리뷰] VLS: Steering Pretrained Robot Policies via Vision-Language Models

arXiv에 게시된 'VLS: Steering Pretrained Robot Policies via Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Vision-Language Models #Policy Steering #Inference-Time Adaptation #Out-of-Distribution Generalization #Diffusion Models #Generative Policies

2026년 2월 4일

[논문리뷰] Training Data Efficiency in Multimodal Process Reward Models

Haolin Liu이 arXiv에 게시한 'Training Data Efficiency in Multimodal Process Reward Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Process Reward Models (MPRMs)#Data Efficiency #Monte Carlo Annotation #Data Selection #Balanced-Information Score (BIS)#Label Mixture #Label Reliability #Computational Cost Reduction

2026년 2월 4일

[논문리뷰] TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents

Qiushi Sun이 arXiv에 게시한 'TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Test-Time Improvement #Diagnostic Evaluation #Trajectory Analysis #Performance Metrics #Behavior Adaptation #Memory Management #POMDP

2026년 2월 4일

[논문리뷰] SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

arXiv에 게시된 'SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #Neural Simulator #Real-to-Sim (R2S)#Robotic Manipulation #Soft-body Dynamics #Gaussian Splatting #Deformable Objects #Action-conditioned Simulation #Long-horizon Simulation

2026년 2월 4일

[논문리뷰] Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

arXiv에 게시된 'Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #LLM #Text-to-Image #Transformer #Semantic Routing #Feature Fusion #Dynamic Conditioning #Generative AI

2026년 2월 4일

[논문리뷰] Self-Hinting Language Models Enhance Reinforcement Learning

arXiv에 게시된 'Self-Hinting Language Models Enhance Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #GRPO #Sparse Rewards #Self-Hinting #Policy Optimization #Adaptive Curriculum #On-Policy Training

2026년 2월 4일

[논문리뷰] Rethinking the Trust Region in LLM Reinforcement Learning

arXiv에 게시된 'Rethinking the Trust Region in LLM Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #Reinforcement Learning #Trust Region #PPO #DPPO #Policy Optimization #Training Stability #Divergence Approximation

2026년 2월 4일

[논문리뷰] Residual Context Diffusion Language Models

arXiv에 게시된 'Residual Context Diffusion Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Language Models #Residual Learning #Context Aggregation #Parallel Decoding #Masked Denoising #Reasoning Benchmarks #Entropy Weighting

2026년 2월 4일

[논문리뷰] Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

arXiv에 게시된 'Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization' 논문에 대한 자세한 리뷰입니다.

#Review #Auto-Regressive Video Generation #KV-Cache Quantization #Memory Optimization #Long Video Generation #Video Diffusion Models #Semantic-Aware Smoothing #Progressive Residual Quantization

2026년 2월 4일

[논문리뷰] PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR

Alejandro Lozano이 arXiv에 게시한 'PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Scientific QA #Information Retrieval #Verifiable Rewards #Biomedical Domain #Search Agents #Dataset Generation

2026년 2월 4일

[논문리뷰] OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Yiyan Ji이 arXiv에 게시한 'OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Omni-modal LLMs #Token Compression #Modality-Asymmetric #Video Pruning #Audio Selection #Efficiency #Large Language Models #Spatio-Temporal

2026년 2월 4일

[논문리뷰] HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing

arXiv에 게시된 'HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse Attention #KV Cache Sharing #Hybrid Attention #Long-Context LLMs #Memory Optimization #Token Selection #Transformer Architecture

2026년 2월 4일

[논문리뷰] HY3D-Bench: Generation of 3D Assets

arXiv에 게시된 'HY3D-Bench: Generation of 3D Assets' 논문에 대한 자세한 리뷰입니다.

#Review #3D Generation #Dataset #Benchmark #AIGC #Watertight Mesh #Part-level Decomposition #Foundation Model #Robotics

2026년 2월 4일