Review

[논문리뷰] UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

arXiv에 게시된 'UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset' 논문에 대한 자세한 리뷰입니다.

#Review #Ultra-High-Resolution #Text-to-Image Generation #Diffusion Models #Large-Scale Dataset #Frequency-Aware Training #Detail Enhancement #Image Synthesis

2025년 10월 29일

[논문리뷰] Tongyi DeepResearch Technical Report

arXiv에 게시된 'Tongyi DeepResearch Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic LLM #Deep Research #Information Seeking #Reinforcement Learning #Synthetic Data #Context Management #Tool Use #Open-source AI

2025년 10월 29일

[논문리뷰] STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence

arXiv에 게시된 'STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #Audio Intelligence #Spatio-Temporal Reasoning #4D Audio #Benchmark #Large Audio-Language Models #Perceptual Reasoning #Multimodal LLMs

2025년 10월 29일

[논문리뷰] Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

arXiv에 게시된 'Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance' 논문에 대한 자세한 리뷰입니다.

#Review #Mixture-of-Experts (MoE)#Diffusion Transformers (DiTs)#Routing Guidance #Semantic Specialization #Contrastive Learning #Image Generation #Flow Matching

2025년 10월 29일

[논문리뷰] RoboOmni: Proactive Robot Manipulation in Omni-modal Context

arXiv에 게시된 'RoboOmni: Proactive Robot Manipulation in Omni-modal Context' 논문에 대한 자세한 리뷰입니다.

#Review #Robotic Manipulation #Multimodal LLMs #Vision-Language-Action #Proactive AI #Omni-modal Learning #Intent Recognition #Contextual Instructions

2025년 10월 29일

[논문리뷰] Rethinking Visual Intelligence: Insights from Video Pretraining

Ahmad Rahimi이 arXiv에 게시한 'Rethinking Visual Intelligence: Insights from Video Pretraining' 논문에 대한 자세한 리뷰입니다.

#Review #Video Diffusion Models #Visual Intelligence #Pretraining #Foundation Models #Low-resource Learning #Inductive Biases #Visual Reasoning #Image-to-Image Tasks

2025년 10월 29일

[논문리뷰] Repurposing Synthetic Data for Fine-grained Search Agent Supervision

arXiv에 게시된 'Repurposing Synthetic Data for Fine-grained Search Agent Supervision' 논문에 대한 자세한 리뷰입니다.

#Review #Search Agents #LLM #Reinforcement Learning #Synthetic Data #Reward Shaping #Entity-aware Reward #Policy Optimization #Knowledge-intensive Tasks

2025년 10월 29일

[논문리뷰] ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?

Ian L. V. Roque이 arXiv에 게시한 'ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Astrophysics Research #Reproducibility Benchmark #Large Language Models #Scientific Workflow #Code Execution #Evaluation Framework

2025년 10월 29일

[논문리뷰] PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding

Denis Cavallucci이 arXiv에 게시한 'PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding' 논문에 대한 자세한 리뷰입니다.

#Review #Patent Text Embedding #Benchmark #Multi-task Learning #Patent Retrieval #Sentence Embeddings #Knowledge Distillation #Cross-Domain Retrieval #Prompt Engineering

2025년 10월 29일

[논문리뷰] PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

Lan Xu이 arXiv에 게시한 'PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #3D Part Segmentation #3D Dataset #Hierarchical Annotation #Fine-Grained Segmentation #Textured Meshes #3D Part Understanding #Part-Centric Question Answering #Crowdsourcing

2025년 10월 29일

[논문리뷰] ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking

arXiv에 게시된 'ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Parallel Thinking #Information Seeking #LLM Agents #Context Window Optimization #Exploration Efficiency #Reasoning Aggregation #Tool Use

2025년 10월 29일

[논문리뷰] OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents

arXiv에 게시된 'OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Agents #Tool Invocation #Benchmark #Model Context Protocol (MCP)#GUI Automation #Computer-Use Agents #Evaluation Metrics

2025년 10월 29일

[논문리뷰] Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

arXiv에 게시된 'Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Visual Reasoning #Latent Space #Sketch Generation #Visual Thinking #Autoregressive Generation #Interpretability

2025년 10월 29일

[논문리뷰] InteractComp: Evaluating Search Agents With Ambiguous Queries

Yani Fan이 arXiv에 게시한 'InteractComp: Evaluating Search Agents With Ambiguous Queries' 논문에 대한 자세한 리뷰입니다.

#Review #Search Agents #Interactive AI #Ambiguous Queries #Benchmarking #Language Agents #Information Retrieval #Overconfidence #Reinforcement Learning

2025년 10월 29일

[논문리뷰] Group Relative Attention Guidance for Image Editing

arXiv에 게시된 'Group Relative Attention Guidance for Image Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Image Editing #Diffusion Transformers #Attention Mechanism #Guidance Mechanism #Controllability #Fine-grained Control #GRAG

2025년 10월 29일

[논문리뷰] Generalization or Memorization: Dynamic Decoding for Mode Steering

arXiv에 게시된 'Generalization or Memorization: Dynamic Decoding for Mode Steering' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models (LLMs)#Generalization #Memorization #Information Bottleneck (IB)#Activation Steering #Decoding Strategy #Causal Intervention #LLM Reliability

2025년 10월 29일

[논문리뷰] Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents

arXiv에 게시된 'Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Generalist AI #Game Agents #Multimodal Learning #Foundation Models #ReAct #Sparse Thinking #Continual Pre-training #Human-Native Interaction

2025년 10월 29일

[논문리뷰] FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling

arXiv에 게시된 'FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling' 논문에 대한 자세한 리뷰입니다.

#Review #Function Calling #Multi-Turn Interaction #Large Language Models (LLMs)#Data Synthesis #Agentic AI #Tool Use #Chain-of-Thought (CoT)#Reinforcement Learning

2025년 10월 29일

[논문리뷰] From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

arXiv에 게시된 'From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA)#3D Spatial Reasoning #Embodied AI #Foundation Models #Multimodal Fusion #Robot Manipulation #Modality Transferability #Action Grounding

2025년 10월 29일

[논문리뷰] Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning

arXiv에 게시된 'Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Language Models #Critiquing #Two-Stage Optimization #Actor-Critic #Scalable Oversight #Discriminability #Helpfulness

2025년 10월 29일