SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling 事件

SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling arXiv:2605.30750v1 Announce Type: new Abstract: In the era of Large Video-Language Models (LVLMs), the computational necessity of sparse frame sampling creates a fundamental ``temporal gap'', rendering models blind to critical causal transitions. Existing solutions relying on generative hallucination (e.g., latent diffusion) or autoregressive extrapolation often fail to maintain semantic consistency over long hori