arXiv:2607.15374v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in th

中文全文翻译正在补齐，可先查看下方英文原文。

[Submitted on 16 Jul 2026]

Title:Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning

View a PDF of the paper titled Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning, by Kazi Sajeed Mehrab and 6 other authors

View PDF

Abstract:Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for objects. We propose Object-Part Hierarchical Reflective Grounding (OP-HRG), a coarse-to-fine reasoning-guided grounding strategy that first localizes the parent object and then the part within it. A self-check then reflects on the result, with an extension to re-encode the predicted crop to inspect the region it is correcting. We introduce a part-aware GRPO framework to train our pipeline with stage-wise rewards. A 4B model trained this way outperforms 7B grounding LLMs and SAM3 across PascalPart, PartImageNet, and InstructPart, and transfers to reasoning segmentation.

Submission history

From: Kazi Sajeed Mehrab [

view email

]

[v1]

Thu, 16 Jul 2026 18:18:31 UTC (25,296 KB)