paper-with-me

홈 › Papers

ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model

2025-08-11 · Weitai Kang, Weiming Zhuang, Zhizhong Li, Yan Yan, Lingjuan Lyu arxiv

Fine-grained multimodal capability in Multimodal Large Language Models (MLLMs) has emerged as a critical research direction, particularly for tackling the visual grounding (VG) problem. Despite the strong performance achieved by existing approaches, they often employ disparate design choices when fine-tuning MLLMs for VG, lacking systematic verification to support these designs. To bridge this gap, this paper presents a comprehensive study of various design choices that impact the VG performance of MLLMs. We conduct our analysis using LLaVA-1.5, which has been widely adopted in prior empirical studies of MLLMs. While more recent models exist, we follow this convention to ensure our findings remain broadly applicable and extendable to other architectures. We cover two key aspects: (1) exploring different visual grounding paradigms in MLLMs, identifying the most effective design, and providing our insights; and (2) conducting ablation studies on the design of grounding data to optimize MLLMs' fine-tuning for the VG task. Finally, our findings contribute to a stronger MLLM for VG, achieving improvements of +5.6% / +6.9% / +7.0% on RefCOCO/+/g over the LLaVA-1.5.

📄 PDF Abstract BibTeX arXiv:2508.08066

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations

2026-05-09 · Gabriele Lombardo, Luigi Maiorana, Liliana Lo Presti, Marco La Cascia arxiv

Visual Grounding benchmarks assume that the object described by a referring expression is always present in the image, and grounding models are therefore rarely evaluated under semantically mismatched captions. In such c…

Referring ExpressionVisual Grounding

Investigating Compositional Challenges in Vision-Language Models for Visual Grounding

2024-01-01 · CVPR 2024 1 · Yunan Zeng, Yan Huang, Jinjin Zhang, Zequn Jie 외

Pre-trained vision-language models (VLMs) have achieved high performance on various downstream tasks which have been widely used for visual grounding tasks in a weakly supervised manner. However despite the performan…

AttributeRelationVisual Grounding

Attending Self-Attention: A Case Study of Visually Grounded Supervision in Vision-and-Language Transformers

2021-08-01 · ACL 2021 5 · Jules Samaran, Noa Garcia, Mayu Otani, Chenhui Chu 외

The impressive performances of pre-trained visually grounded language models have motivated a growing body of research investigating what has been learned during the pre-training. As a lot of these models are based on Tr…

Language ModelingLanguage ModellingVisual Grounding

mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation

2025-05-29 · Chan-Wei Hu, Yueqi Wang, Shuo Xing, Chia-Ju Chen 외

Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning. However, they remain limited by static training data, susc…

Question AnsweringRAGRe-RankingRetrieval+3

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

2025-06-05 · Tianxu Wang, Zhuofan Zhang, Ziyu Zhu, Yue Fan 외

3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3…

3D visual groundingObjectReferring ExpressionSpatial Reasoning+1