InSight-doc: Agentic Visual Perception for Long-Document Understanding
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - InSight-doc is an agentic visual perception framework that treats image resolution as an adaptive reasoning-time resource, starting from low-resolution pages and selectively zooming into regions for evidence, rather than using an external retriever. It matters because it cuts both hallucination and inference cost on long, visually rich documents while improving accuracy.
- Training pipeline combines SFT on a 17.9K-example active-perception corpus with region-level zoom-in trajectories, plus 19.2K hard RL examples (SFT+RL).
- InSight-doc-8B improves over the baseline by 4.3–16.4 accuracy points across document VQA benchmarks.
- On long documents, it reduces hallucination by over 40% and inference latency by 41%–68% while retaining an accuracy lead.
- Retriever-free design targets "context rot" from many-page inputs; code, datasets, and model are released publicly.
Sources (1)
InSight-doc: Agentic Visual Perception for Long-Document Understanding
TL;DR - InSight-doc is an agentic visual perception framework that treats image resolution as an adaptive reasoning-time resource, starting from low-resolution pages and selectively zooming into regions for evidence, rather than using an external retriever. It matters because it cuts both hallucination and inference cost on long, visually rich documents while improving accuracy.
- Training pipeline combines SFT on a 17.9K-example active-perception corpus with region-level zoom-in trajectories, plus 19.2K hard RL examples (SFT+RL).
- InSight-doc-8B improves over the baseline by 4.3–16.4 accuracy points across document VQA benchmarks.
- On long documents, it reduces hallucination by over 40% and inference latency by 41%–68% while retaining an accuracy lead.
- Retriever-free design targets "context rot" from many-page inputs; code, datasets, and model are released publicly.