paper-with-me

홈 › Papers

RegionReasoner: Region-Grounded Multi-Round Visual Reasoning

2026-02-03 · Wenfang Sun, Hao Chen, Yingjun Du, Yefeng Zheng, Cees G. M. Snoek arxiv

Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual contexts. To address this limitation, we introduce a new multi-round visual reasoning benchmark with training and test sets spanning both detection and segmentation tasks, enabling systematic evaluation under iterative reasoning scenarios. We further propose RegionReasoner, a reinforcement learning framework that enforces grounded reasoning by requiring each reasoning trace to explicitly cite the corresponding reference bounding boxes, while maintaining semantic coherence via a global-local consistency reward. This reward extracts key objects and nouns from both global scene captions and region-level captions, aligning them with the reasoning trace to ensure consistency across reasoning steps. RegionReasoner is optimized with structured rewards combining grounding fidelity and global-local semantic alignment. Experiments on detection and segmentation tasks show that RegionReasoner-7B, together with our newly introduced benchmark RegionDial-Bench, considerably improves multi-round reasoning accuracy, spatial grounding precision, and global-local consistency, establishing a strong baseline for this emerging research direction.

📄 PDF Abstract BibTeX arXiv:2602.03733

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningVisual Reasoning

Similar Papers 제목 키워드 기반

Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models

2024-04-19 · Chuofan Ma, Yi Jiang, Jiannan Wu, Zehuan Yuan 외

We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability. Beyond holistic image understanding, Groma is adept at region-level tasks such as region captioning a…

Language ModelingLanguage ModellingLarge Language ModelMultimodal Large Language Model+3

GLaMM: Pixel Grounding Large Multimodal Model

2023-11-06 · CVPR 2024 1 · Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly, Abdelrahman Shaker 외

Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to…

Conversational Question AnsweringImage CaptioningmodelReferring Expression+4

Flexible Visual Grounding

2022-05-01 · ACL 2022 5 · Yongmin Kim, Chenhui Chu, Sadao Kurohashi

Existing visual grounding datasets are artificially made, where every query regarding an entity must be able to be grounded to a corresponding image region, i.e., answerable. However, in real-world multimedia data such a…

ArticlesVisual Grounding

Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification

2026-02-21 · Haoyu Zhang, Yuwei Wu, Pengxiang Li, Xintong Zhang 외 arxiv

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to h…

Multimodal Reasoning

Grounded Reinforcement Learning for Visual Reasoning

2025-05-29 · Gabriel Sarch, Snigdha Saha, Naitik Khandelwal, Ayush Jain 외

While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Spatial Reasoning+1