#Large Vision-Language Models

6개의 포스트

[논문리뷰] AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration

Xinchao Wang이 arXiv에 게시한 'AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration' 논문에 대한 자세한 리뷰입니다.

#Review #Membership Inference Attack #Agentic Framework #Strategy Self-Exploration #Large Vision-Language Models #Privacy Auditing

2026년 4월 2일

[논문리뷰] VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning

Yansong Tang이 arXiv에 게시한 'VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Tool-integrated Visual Reasoning #Referring Grounded Reasoning #Agentic Reinforcement Learning #Self-Correction #Large Vision-Language Models #Chain-of-Thought #Tool Refinement

2025년 12월 8일

[논문리뷰] SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

arXiv에 게시된 'SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Navigation #Large Vision-Language Models #Visual Prompt #Reinforcement Fine-Tuning #Policy Optimization #Embodied AI #Spatial Reasoning #Perception Errors

2025년 12월 4일

[논문리뷰] Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

Jiaxin Yuan이 arXiv에 게시한 'Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings' 논문에 대한 자세한 리뷰입니다.

#Review #Hallucination Mitigation #Large Vision-Language Models #Textual Embeddings #Multimodal Reasoning #Attention Mechanism #Visual Grounding #Modality Imbalance

2025년 11월 9일

[논문리뷰] VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

arXiv에 게시된 'VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Code Generation #SVG #Visual Representation #Benchmark #Large Vision-Language Models #Agentic AI #Reasoning

2025년 11월 9일

[논문리뷰] CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Jianze Liang이 arXiv에 게시한 'CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #GUI Agents #Reinforcement Learning #Planner-Executor Architecture #Decoupled Training #Large Vision-Language Models #Specialization #Generalization #Computer Use Agent

2025년 8월 28일