Ji Huang

Your VLM Already Knows When: Training-Free Temporal Grounding by Asking Yes or No

FV-Action, the training-free method built on this analysis, is the strongest training-free result on this benchmark; it surpasses every TVG-trained model evaluated zero-shot on TACoS, and improves over direct prediction on ActivityNet Captions and QVHighlights, with no temporal supervision at any stage.