Review

[논문리뷰] FASA: Frequency-aware Sparse Attention

arXiv에 게시된 'FASA: Frequency-aware Sparse Attention' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse Attention #KV Cache Optimization #Rotary Positional Embedding (RoPE)#Frequency Chunks (FCs)#LLMs #Long-Context #Training-Free

2026년 2월 4일

[논문리뷰] EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models

Ziyi Bai이 arXiv에 게시한 'EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Humanoid Robots #Vision-Language Models #Task Planning #Egocentric Control #Mobile Manipulation #Active Perception #Human-Robot Interaction #Real-World Deployment

2026년 2월 4일

[논문리뷰] ERNIE 5.0 Technical Report

HasuerYu이 arXiv에 게시한 'ERNIE 5.0 Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Foundation Model #Autoregressive #Mixture-of-Experts #Elastic Training #Reinforcement Learning #Unified Architecture #Sparse MoE #Efficient Deployment

2026년 2월 4일

[논문리뷰] BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation

Xiaohua Wang이 arXiv에 게시한 'BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation' 논문에 대한 자세한 리뷰입니다.

#Review #Self-Supervised Learning #Code Generation #Documentation Generation #Back-Translation #Reinforcement Learning #Large Language Models (LLMs)#Code-Documentation Alignment #Low-Resource Languages

2026년 2월 4일

[논문리뷰] AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations

arXiv에 게시된 'AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations' 논문에 대한 자세한 리뷰입니다.

#Review #Scientific Illustration Generation #Long-form Text-to-Image #Agentic Framework #Reasoned Rendering #Layout Planning #Text Refinement #FigureBench #VLM-as-a-judge

2026년 2월 4일

[논문리뷰] Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning

arXiv에 게시된 'Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Agent Efficiency #Context Management #Thought Omission #Observation Omission #Reinforcement Learning #Adaptive Policy

2026년 2월 4일

[논문리뷰] A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces

arXiv에 게시된 'A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic RAG #Hierarchical Retrieval #LLM Tool Use #Multi-hop QA #Context Efficiency #Dynamic Strategy #Retrieval-Augmented Generation

2026년 2월 4일

[논문리뷰] daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently

arXiv에 게시된 'daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Horizon Agency #Data Synthesis #Pull Request Chains #Software Evolution #LLM Training #Agentic AI #Self-Distillation #Code Generation

2026년 2월 3일

[논문리뷰] WideSeek: Advancing Wide Research via Multi-Agent Scaling

Zhongtao Jiang이 arXiv에 게시한 'WideSeek: Advancing Wide Research via Multi-Agent Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Wide Research #Multi-Agent Systems #Reinforcement Learning #Information Seeking #Benchmarking #LLM Agents #Knowledge Graphs

2026년 2월 3일

[논문리뷰] Unified Personalized Reward Model for Vision Generation

arXiv에 게시된 'Unified Personalized Reward Model for Vision Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Reward Model #Vision Generation #Personalized Learning #Context-Adaptive Reasoning #Direct Preference Optimization (DPO)#Reinforcement Learning (RL)#Multimodal Learning #Group Relative Policy Optimization (GRPO)

2026년 2월 3일

[논문리뷰] Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection

Jae-Joon Kim이 arXiv에 게시한 'Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection' 논문에 대한 자세한 리뷰입니다.

#Review #Sparse Attention #Long-Context Inference #LLMs #Token Selection #Efficiency #Transformer #Dynamic Sparsity

2026년 2월 3일

[논문리뷰] SimpleGPT: Improving GPT via A Simple Normalization Strategy

Rong Xiao이 arXiv에 게시한 'SimpleGPT: Improving GPT via A Simple Normalization Strategy' 논문에 대한 자세한 리뷰입니다.

#Review #Transformer Optimization #Normalization Strategy #Hessian Spectral Norm #Learning Rate Stability #Large Language Models #SimpleNorm #Second-Order Optimization

2026년 2월 3일

[논문리뷰] SWE-World: Building Software Engineering Agents in Docker-Free Environments

arXiv에 게시된 'SWE-World: Building Software Engineering Agents in Docker-Free Environments' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering Agents #LLM #Docker-Free #Execution Simulation #Reinforcement Learning #Supervised Fine-tuning #World Model

2026년 2월 3일

[논문리뷰] SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

arXiv에 게시된 'SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering Agents #Post-Training #Supervised Fine-Tuning #Reinforcement Learning #Language Server Protocol #SWE-bench #Code Navigation #LLM

2026년 2월 3일

[논문리뷰] Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

arXiv에 게시된 'Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Unified Framework #Multimodal AI #Embodied AI #Physical Understanding #Long-term Consistency #AI Agents #Generative Models

2026년 2월 3일

[논문리뷰] Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

arXiv에 게시된 'Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reasoning #Parallel Thinking #Efficiency Optimization #2D Probing #Consensus-based Early Stopping #Deviation-based Branch Pruning #Test-Time Scaling

2026년 2월 3일

[논문리뷰] No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs

arXiv에 게시된 'No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Chain-of-Thought #LLM Planning #Probing Methods #Uncertainty Estimation #Reasoning Dynamics #Model Interpretability

2026년 2월 3일

[논문리뷰] MARS: Modular Agent with Reflective Search for Automated AI Research

arXiv에 게시된 'MARS: Modular Agent with Reflective Search for Automated AI Research' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous AI #Agent Framework #Machine Learning Engineering #Monte Carlo Tree Search #Reflective Learning #Modular Programming #Code Generation #Resource Management

2026년 2월 3일

[논문리뷰] Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

arXiv에 게시된 'Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Reasoning #Instruction Purification #Interference Tokens #Sample Efficiency #Policy Optimization #Verifiable Rewards

2026년 2월 3일

[논문리뷰] Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

arXiv에 게시된 'Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation' 논문에 대한 자세한 리뷰입니다.

#Review #DeepResearch #Rubric Generation #Human Preferences #Reinforcement Learning #Multi-agent Systems #LLM Evaluation #Reward Modeling

2026년 2월 3일