Self-Augmented Visual Contrastive Decoding
Paper • 2510.13315 • Published
Multimodal-Learning
-
-
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
Paper • 2412.03735 • Published • 1 -
Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
Paper • 2604.13313 • Published • 12 -
Video Generation Models: A Survey of Post-Training and Alignment
Paper • 2610.00812 • Published • 60