Building a Precise Video Language with Human-AI Oversight
Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, grounded by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce CHAI (Critique-based Human-AI Oversight), a framework where trained experts critique and revise model-generated pre-captions into improved post-captions. This division of labor impr...
| Authors | Zhiqiu Lin, Chancharik Mitra, Siyuan Cen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 22 April 2026 |
| Last updated at source | 26 April 2026 |
Connected in the knowledge graph
- chancharikm/CHAI_testsetDataset · cited by
- chancharikm/CHAI_SFT_model_8bModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.