CORTEXA
← Browse
arxivcs.CVcs.AI2026-07-07

Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning

Yake Wei, Yuan Wang, Fengyun Rao, Jing Lyu, Di Hu

Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''. A basic operation in this reasoning process is to zoom in on regions of interest (often represented with bounding boxes) to acquire finer visual details. In this paper, we propose \textbf{Seg}mentation before \textbf{Answer}ing (SegAnswer), which shifts the unit of zoom-in from the popular bounding box to pixel-level segmentation mask. By employing fine-grained masks to isolate the target area from cluttered environments, segmented visual input yields a more precise region of interest, effectively filtering out redundant background and interfering objects. Furthermore, the discrete patches of segmented visual input align more seamlessly with how MLLMs structure visual tokens via positional embeddings. In experiments, we evaluate SegAnswer across diverse benchmarks, including high-resolution perception, general perception, and hallucination. It achieves consistent improvements and also exhibits considerable performance on segmentation tasks, validating its capability for reliable pixel grounding.

View free PDFSource page

Related papers

arxivcs.AIcs.CV2026-07-07

Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

Han-Jun Ko, Jr-Jen Chen, Haobo Yuan, Hsin-Ying Lee, Tiancheng Shen, Ming-Hsuan Yang, et al.

Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between…

View free PDFSource page
arxivcs.CVcs.AI2026-07-10

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents

Yang Chen, Yunwen Li, Yufan Shen, Minghao Liu, Tianyu Zheng, Bin Fu, et al.

Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual groundin…

View free PDFSource page
arxivcs.CVcs.AI2026-07-15

GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning

Kaicong Huang, Weiheng Oh, Jack M. Reilly, Thomas Guggisberg, Ruimin Ke

Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supervised video models require task-specific annotations, while applying vision-language models (VLMs) directly to long onboard video…

View free PDFSource page
arxivcs.CVcs.AIcs.CL2026-06-30

PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding

Duc Cao Dinh, Khai Le-Duc, Florent Draye, Chris Ngo, Terry Jingchen Zhang, Bernhard Schölkopf, et al.

3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform reasoning over the entire scene, leading to ambiguous predictions and high computational cost, especially in cluttered environments.…

View free PDFSource page
arxivcs.CVcs.AIeess.IV2026-07-14

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

Jinjian Wu, Jiaqi Tang, Wei Wei, Yingying Yan, Jianmin Chen, Botong Geng, et al.

Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches based on multimodal large language models (MLLMs) introduce textual reasoning for quality prediction, yet their judgments rely heavi…

View free PDFSource page