paper-with-me

Papers

Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning

2026-07-16 · Kazi Sajeed Mehrab, Hani Alomari, Najibul Haque Sarker, Chia-Wei Tang, Zaber Ibn Abdul Hakim, Anuj Karpatne, Chris Thomas arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.15374

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningVisual Grounding

Similar Papers 제목 키워드 기반

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

2025-05-20 · Sule Bai, Mingxing Li, Yong liu, Jing Tang 외

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, part…

Large Language ModelMultimodal Large Language ModelReinforcement Learning (RL)Visual Grounding

REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation

2025-12-29 · Fulin Shi, Wenyi Xiao, Bin Chen, Liang Din 외 arxiv

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained…

Visual Reasoning

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

2026-05-31 · Wanlong Fang, Tianle Zhang, Wen Tao, Alvin Chan arxiv

Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment. We introduce Partial Information Decomposition (PID) as a decision-level framework that separates unique, …

Multimodal Reasoning

Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding Enhancement

2026-02-04 · Zipeng Zhu, Zhanghao Hu, Qinglin Zhu, Yuxi Hong 외 arxiv

Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to a uniform pretraining resolution, often …

Visual LocalizationQuestion AnsweringObject RecognitionVisual Grounding

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR

2026-03-27 · Jinda Lu, Junkang Wu, Jinghan Li, Kexin Huang 외 arxiv

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However,…

Reinforcement LearningMultimodal ReasoningLogical ReasoningVisual Grounding