Review

[논문리뷰] Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data

arXiv에 게시된 'Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data' 논문에 대한 자세한 리뷰입니다.

#Review #Omnimodal Large Models #Mixture-of-Experts (MoE)#Language-Centric AI #Multimodal Understanding #Multimodal Generation #Progressive Training #Omni-Modality 3D RoPE

2025년 11월 17일

[논문리뷰] UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

arXiv에 게시된 'UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity' 논문에 대한 자세한 리뷰입니다.

#Review #Self-Supervised Learning #Segmentation #Granularity Control #SAM #Foundation Models #Unsupervised Learning #Image Segmentation #Video Segmentation

2025년 11월 17일

[논문리뷰] UFO^3: Weaving the Digital Agent Galaxy

arXiv에 게시된 'UFO^3: Weaving the Digital Agent Galaxy' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent Systems #Cross-Device Orchestration #LLM-Powered Agents #Task Constellation #Directed Acyclic Graph (DAG)#Agent Interaction Protocol (AIP)#Fault Tolerance #Asynchronous Execution

2025년 11월 17일

[논문리뷰] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models

Qingyang Liu이 arXiv에 게시한 'TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generative Models #Visual Reasoning #Benchmarking #Image-to-Video #TiViBench #VideoTPO #Prompt Optimization

2025년 11월 17일

[논문리뷰] Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models

arXiv에 게시된 'Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Test-Time Adaptation #Zero-Shot Generalization #Spectral Decomposition #Latent Space Steering #SVD #Out-of-Distribution

2025년 11월 17일

[논문리뷰] Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

arXiv에 게시된 'Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance' 논문에 대한 자세한 리뷰입니다.

#Review #Model Souping #Large Language Models #Weighted Averaging #Benchmark Optimization #State-of-the-Art #Category Experts #Parameter Averaging #Post-training

2025년 11월 17일

[논문리뷰] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

Bo Du이 arXiv에 게시한 'SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Safety Alignment #Rule-Governed RL #Self-Rewarded Learning #MLLM Safety #Policy Optimization #Safety Benchmarking #Compositional Robustness

2025년 11월 17일

[논문리뷰] Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

arXiv에 게시된 'Part-X-MLLM: Part-aware 3D Multimodal Large Language Model' 논문에 대한 자세한 리뷰입니다.

#Review #3D Multimodal LLM #Part-aware #3D Generation #3D Editing #3D Understanding #Bounding Box #Structured Program #Dual-encoder

2025년 11월 17일

[논문리뷰] P1: Mastering Physics Olympiads with Reinforcement Learning

Haiyuan Wan이 arXiv에 게시한 'P1: Mastering Physics Olympiads with Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Physics Reasoning #Agentic AI #Olympiad Problems #Post-Training #Knowledge Transfer

2025년 11월 17일

[논문리뷰] OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation

arXiv에 게시된 'OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation' 논문에 대한 자세한 리뷰입니다.

#Review #Earth Observation #Foundation Model #Multimodal Learning #Self-supervised Learning #Latent Image Modeling #Vision Transformer #Spatio-temporal

2025년 11월 17일

[논문리뷰] NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

arXiv에 게시된 'NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Model #Direct Preference Optimization #World Model #Reward Learning #Robotics #Embodied AI #Flow-Matching

2025년 11월 17일

[논문리뷰] MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

cyyang822이 arXiv에 게시한 'MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Research Agent #Tool-Augmented Reasoning #Interaction Scaling #Large Language Models #Reinforcement Learning #Context Management #Open-Source AI

2025년 11월 17일

[논문리뷰] MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model

Bo Yan이 arXiv에 게시한 'MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model' 논문에 대한 자세한 리뷰입니다.

#Review #Microscopy VQA #Multimodal LLM #Weak Supervision #Graph Neural Networks #Dataset Generation #Biomedical Imaging #Scientific Reasoning #Cross-Modal Consistency

2025년 11월 17일

[논문리뷰] LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering

arXiv에 게시된 'LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Software Engineering #Long-Context #Interactive Benchmark #Tool Usage #Memory Management #Bias-Free Evaluation #Multi-Turn

2025년 11월 17일

[논문리뷰] Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?

Lingming Zhang이 arXiv에 게시한 'Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering Agents #LLM Agents #Self-Evolution #On-the-Fly Learning #Tool Creation #SWE-bench #Autonomous Systems #Code Generation

2025년 11월 17일

[논문리뷰] Genomic Next-Token Predictors are In-Context Learners

arXiv에 게시된 'Genomic Next-Token Predictors are In-Context Learners' 논문에 대한 자세한 리뷰입니다.

#Review #In-Context Learning (ICL)#Genomic Sequences #Next-Token Prediction #Large Language Models (LLMs)#Modality-Agnostic AI #Meta-Learning #Bitstring Program Synthesis #Evo2

2025년 11월 17일

[논문리뷰] Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing

arXiv에 게시된 'Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing' 논문에 대한 자세한 리뷰입니다.

#Review #Serendipity Discovery #Knowledge Graphs #Drug Repurposing #LLMs #KGQA #RNS Metric #Biomedical AI

2025년 11월 17일

[논문리뷰] AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

Hongyu Lin이 arXiv에 게시한 'AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing' 논문에 대한 자세한 리뷰입니다.

#Review #Telemarketing #Large Language Models #Persuasive Dialogue #Reinforcement Learning #Bayesian Optimization #Dynamic Prompting #Dialogue Systems

2025년 11월 17일

[논문리뷰] A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain

Meng Jiang이 arXiv에 게시한 'A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain' 논문에 대한 자세한 리뷰입니다.

#Review #Decentralized RAG #Blockchain #Smart Contracts #Source Reliability #Large Language Models #Retrieval Augmented Generation #Trustworthy AI

2025년 11월 17일

[논문리뷰] miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward

Farzan Farnia이 arXiv에 게시한 'miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward' 논문에 대한 자세한 리뷰입니다.

#Review #Automated Theorem Proving #Autoformalization #Benchmark Dataset #miniF2F #Lean Language #Large Language Models #Mathematical Reasoning #Formal Verification

2025년 11월 16일