[ICLR 2026] VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
Ye Liu
yeliudev
AI & ML interests
Vision & Language
Recent Activity
updated a Space about 13 hours ago
yeliudev/VideoMind-2B upvoted a paper about 21 hours ago
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context upvoted a paper 1 day ago
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map DistillationOrganizations
models 7
yeliudev/VideoMind-2B-FT-QVHighlights
Video-Text-to-Text • Updated • 10 • 1
yeliudev/VideoMind-7B
Video-Text-to-Text • Updated • 36 • 4
yeliudev/VideoMind-2B
Video-Text-to-Text • Updated • 28 • 2
yeliudev/R2-Tuning
Updated • 2
yeliudev/CATNet
Updated
yeliudev/UMT
Updated
yeliudev/ConsNet
Updated