SOURCE-LINKED INTELLIGENCE
The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
Seeing frames in order does not mean representing time. Modern VideoLMs receive ordered video streams, yet their main supervision acts on generated text rather than video-token representations where event dynamics should first emerge. This mismatch allows models to learn temporal answers from shortcuts such as objects, scenes, and language priors, without requiring internal video representations to capture event progression. To address this, we propose VT-Contrast, a representation-level temporal counterfactual objective for VideoLMs. Its design asks where temporal supervision should act and w
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-03T17:14:55.000Z
First collected: 2026-09-21T04:31:57.454Z. This is not the publication date.