Review

[논문리뷰] UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

Yongliang Shen이 arXiv에 게시한 'UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #GUI Automation #Reinforcement Learning #Semi-online RL #Offline RL #Online RL #Patch Module #Multi-turn Interaction #Large Language Models

2025년 9월 16일

[논문리뷰] SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

Heshaam Faili이 arXiv에 게시한 'SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #Instruction Tuning #Domain Adaptation #Retrieval-Augmented Generation #Dataset Creation #Model Editing #Supervised Fine-Tuning

2025년 9월 16일

[논문리뷰] PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

Zhenhao Chen이 arXiv에 게시한 'PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Dataset #LLM Inference #Behavioral Traits #Causal Representation Learning #Big Five #Multimodal AI #Causal Discovery #Human-Computer Interaction

2025년 9월 16일

[논문리뷰] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Yang Zhou이 arXiv에 게시한 'OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling' 논문에 대한 자세한 리뷰입니다.

#Review #4D World Modeling #Multi-Modal Dataset #Multi-Domain Data #Geometric Foundation Models #Video Generation #Spatio-Temporal Data #Dataset Benchmark

2025년 9월 16일

[논문리뷰] Measuring Epistemic Humility in Multimodal Large Language Models

Kaiyang Zhou이 arXiv에 게시한 'Measuring Epistemic Humility in Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models #Hallucination #Epistemic Humility #Benchmark #False-Option Rejection #Visual Question Answering #Scene Graph

2025년 9월 16일

[논문리뷰] Lost in Embeddings: Information Loss in Vision-Language Models

Ivan Vulić이 arXiv에 게시한 'Lost in Embeddings: Information Loss in Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Information Loss #Embeddings #Connectors #k-NN Overlap Ratio #Embedding Reconstruction #Multimodal AI

2025년 9월 16일

[논문리뷰] Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

Shuo Ren이 arXiv에 게시한 'Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Visual Reasoning #Reflection #Reinforcement Learning #Visual Attention #Slow Thinking #Multimodal Agents

2025년 9월 16일

[논문리뷰] Locality in Image Diffusion Models Emerges from Data Statistics

Vincent Sitzmann이 arXiv에 게시한 'Locality in Image Diffusion Models Emerges from Data Statistics' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Locality #Data Statistics #Optimal Denoiser #Wiener Filter #Sensitivity Fields #Generative Models #Inductive Bias

2025년 9월 16일

[논문리뷰] Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

Changlong Yu이 arXiv에 게시한 'Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-objective Reinforcement Learning #LLM Alignment #Dynamic Reward Weighting #Pareto Front Optimization #Hypervolume Indicator #Gradient-based Optimization #Online RL

2025년 9월 16일

[논문리뷰] LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

Lionel M. Ni이 arXiv에 게시한 'LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Models #Multi-Modal Transformers #Drag-based Editing #Explicit Correspondence #Attention Control #Identity Preservation #Training-Free

2025년 9월 16일

[논문리뷰] InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

Wenzhe Cai이 arXiv에 게시한 'InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied AI #3D Scene Dataset #Simulation Environment #Scene Generation #Point-Goal Navigation #Realistic Layouts #Object Interaction #Real-to-Sim

2025년 9월 16일

[논문리뷰] GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

Yixuan Tang이 arXiv에 게시한 'GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings' 논문에 대한 자세한 리뷰입니다.

#Review #Model Pruning #Domain Adaptation #Embedding Models #Gradient Alignment #Fisher Information #Model Compression #LLMs

2025년 9월 16일

[논문리뷰] EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

UVSKKR이 arXiv에 게시한 'EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI' 논문에 대한 자세한 리뷰입니다.

#Review #Ethical Reasoning #Mental Health AI #Benchmark Dataset #Large Language Models #AI Ethics #Clinical Decision Support #Human-in-the-loop

2025년 9월 16일

[논문리뷰] Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

Li Zheng이 arXiv에 게시한 'Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding' 논문에 대한 자세한 리뷰입니다.

#Review #Video Hallucination #Large Video Models (LVMs)#Hierarchical Reasoning #Spatial-Temporal Grounding #Diagnostic Framework #Benchmark Dataset #Multimodal AI

2025년 9월 16일

[논문리뷰] CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

Subasish Das이 arXiv에 게시한 'CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media' 논문에 대한 자세한 리뷰입니다.

#Review #Sentiment Analysis #Narrative Analysis #Decentralized Social Media #Bluesky #Transformer Models #Topic Modeling #Real-time Processing #Data Visualization

2025년 9월 16일

[논문리뷰] X-Part: high fidelity and structure coherent shape decomposition

Yunhan Yang이 arXiv에 게시한 'X-Part: high fidelity and structure coherent shape decomposition' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Decomposition #Diffusion Models #Part-level Generation #Controllable Generation #Bounding Box Prompts #Semantic Features #Interactive Editing #Generative AI

2025년 9월 15일

[논문리뷰] Virtual Agent Economies

William A. Cunningham이 arXiv에 게시한 'Virtual Agent Economies' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Virtual Economy #Multi-Agent Systems #Economic Mechanisms #Governance #Blockchain #Resource Allocation #Agent Alignment

2025년 9월 15일

[논문리뷰] VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

Dong Zhang이 arXiv에 게시한 'VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions' 논문에 대한 자세한 리뷰입니다.

#Review #Voice Style Adaptation #Spoken Language Models #Benchmark #LALM-as-a-Judge #Speech Generation #Multilingual #Evaluation Framework

2025년 9월 15일

[논문리뷰] The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

Jonas Geiping이 arXiv에 게시한 'The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Long-Horizon Tasks #Execution Capability #Scaling Laws #Self-Conditioning #Thinking Models #Agentic AI

2025년 9월 15일

[논문리뷰] QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

Chenyu You이 arXiv에 게시한 'QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading' 논문에 대한 자세한 리뷰입니다.

#Review #High-Frequency Trading #Multi-Agent Systems #Large Language Models #Technical Analysis #Algorithmic Trading #Financial Reasoning #Price-Driven Signals

2025년 9월 15일