AI RESEARCH
SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling
arXiv CS.CV
•
ArXi:2605.30750v1 Announce Type: new 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 horizons, suffering from object vanishing and energetic instability.