V-JEPA-LM pairs video world-model encoders with language models to capture scene dynamics
A new arXiv paper presents V-JEPA-LM, which joins V-JEPA video encoders that learn how scenes change—direction, speed, order, state—from video alone with language models to answer questions beyond static, text-aligned representations.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-16 05:00 · arXiv cs.CV
V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned Representations