Video Generation Models: A Survey of Post-Training and Alignment
Paper • 2610.00812 • Published • 44
Pooyan Fazli
PooyanFazli
AI & ML interests
None yet
Recent Activity
authored a paper about 21 hours ago
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large
Language Models for Video Understanding authored a paper about 21 hours ago
VideoSAVi: Self-Aligned Video Language Models without Human Supervision authored a paper about 21 hours ago
CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory AggregationOrganizations
None yet
upvoted 4
papers 1 day ago
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
Paper • 2412.03735 • Published • 1
VideoA11y: Method and Dataset for Accessible Video Description
Paper • 2502.20480 • Published • 1
VideoSAVi: Self-Aligned Video Language Models without Human Supervision
Paper • 2412.00624 • Published • 2