#artificial intelligence
Jun 2026
APT: Atomic Physical Transitions for Causal Video-Language Understanding
APT-Tune is proposed, a parameter-efficient recipe that teaches VLMs to use causal transitions without forgetting how to answer video questions, and substantially improves APT recall while also improving event-level video transfer.
Shang Wu, Haoran Lu, Song-Lin Liu et al.
· arXiv.org · 0 citations