Junjie Fei
4
Papers
8
Total Citations
Papers (4)
MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
NeurIPS 2025
5
citations
Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description
ICCV 2025
3
citations
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
CVPR 2025
0
citations
WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
ICCV 2025
0
citations