AI RESEARCH
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
arXiv CS.CL
•
ArXi:2605.26014v1 Announce Type: cross Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through textual chain-of-thought (CoT), keyframe selection, repeated frame reinsertion, or external tool use. While effective, such pipelines increase inference-time latency and engineering complexity, and they force temporal-visual evidence to be serialized into text or repeatedly re-encoded from frames.