[논문리뷰] Ego2Web: A Web Agent Benchmark Grounded in Egocentric VideosarXiv에 게시된 'Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos' 논문에 대한 자세한 리뷰입니다.#Review#Multimodal AI Agents#Web-agent Benchmark#Egocentric Video#Visual Grounding#Online Evaluation#LLM-as-a-Judge#Perception-Action Alignment2026년 3월 24일댓글 수 로딩 중
[논문리뷰] 'Does the cafe entrance look accessible? Where is the door?' Towards Geospatial AI Agents for Visual InquiriesXia Su이 arXiv에 게시한 'Does the cafe entrance look accessible? Where is the door? Towards Geospatial AI Agents for Visual Inquiries' 논문에 대한 자세한 리뷰입니다.#Review#Geospatial AI#Multimodal AI Agents#Visual Question Answering#Accessibility#Street View Imagery#Spatial Reasoning#Human-Computer Interaction2025년 8월 22일댓글 수 로딩 중