3 papers
cs.CV2026
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
Ke Ma, Yamin Mao, Weiming Li +5
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it wa…
cs.LG2026
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
Yuchen Yan, Peiyan Zhang, Zhihua Liu +4
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, w…
cs.CV2025
MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction
Xiaoshuai Hao, Yunfeng Diao, Mengchuan Wei +7
Map construction task plays a vital role in providing precise and comprehensive static environmental information essential for autonomous driving systems. Primary sensors include c…