Jag: Direct Box Prediction for Efficient Visual Grounding
Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed for localization. Adapting these representations to box geometry offers a route to direct prediction. We present Jag, which adapts a compact pretrained multimodal model for direct continuous box prediction. A lightweight regression head reads the last valid input-token state, conditioned on the image and referring expression, and predicts all four box coordinates together. Geometric supervision jointly adapts the language backbone, visual merger, and reg...
| Authors | Xiuyuan Zhu, Ke Lu, Hao Wu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 9 October 2026 |
| Last updated at source | 12 October 2026 |
Popularity, last 3 days
0 now (-5 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- xyzzzh/JagModel · cited by
Recent changes
- 16 Oct 2026 Description: Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed f → Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed f
- 16 Oct 2026 Topics added cs.CV removed hf-daily-papers, visual grounding, autoregressive multimodal models, continuous box prediction, regression head, geometric supervision, multimodal representations, direct prediction
Changes detected by Silytics between refreshes of the source.
Models and datasets referencing this paper
- xyzzzh/JagModel
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 Information may be incomplete or out of date.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.