paper-with-me

Papers

Enhancing Spatial Reasoning through Visual and Textual Thinking

2025-07-28 · Xun Liang, Xin Guo, Zhongming Jin, Weihang Pan, Penghui Shang, Deng Cai, Binbin Lin, Jieping Ye arxiv

The spatial reasoning task aims to reason about the spatial relationships in 2D and 3D space, which is a fundamental capability for Visual Question Answering (VQA) and robotics. Although vision language models (VLMs) have developed rapidly in recent years, they are still struggling with the spatial reasoning task. In this paper, we introduce a method that can enhance Spatial reasoning through Visual and Textual thinking Simultaneously (SpatialVTS). In the spatial visual thinking phase, our model is trained to generate location-related specific tokens of essential targets automatically. Not only are the objects mentioned in the problem addressed, but also the potential objects related to the reasoning are considered. During the spatial textual thinking phase, Our model conducts long-term thinking based on visual cues and dialogues, gradually inferring the answers to spatial reasoning problems. To effectively support the model's training, we perform manual corrections to the existing spatial reasoning dataset, eliminating numerous incorrect labels resulting from automatic annotation, restructuring the data input format to enhance generalization ability, and developing thinking processes with logical reasoning details. Without introducing additional information (such as masks or depth), our model's overall average level in several spatial understanding tasks has significantly improved compared with other models.

📄 PDF Abstract BibTeX arXiv:2507.20529

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringSpatial ReasoningLogical Reasoning

Similar Papers 제목 키워드 기반

I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction

2024-07-19 · Zaiqiao Meng, Hao Zhou, Yifang Chen

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. Howeve…

3D ReconstructionSpatial ReasoningVisual Reasoning

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

2025-06-11 · Junfei Wu, Jian Guan, Kaituo Feng, Qiang Liu 외

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, exis…

Multimodal ReasoningSpatial Reasoning

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning

2025-10-03 · Chashi Mahiul Islam, Oteo Mamo, Samuel Jacob Chacko, Xiuwen Liu 외 arxiv

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM …

Multimodal ReasoningMulti-Task LearningSpatial Reasoning

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

2025-05-18 · Yang Liu, Ming Ma, Xiaomin Yu, Pengxiang Ding 외

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clou…

Knowledge DistillationSpatial Reasoning

Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs

2025-06-27 · Amirmohammad Izadi, Mohammad Ali Banayeeanzade, Fatemeh Askari, Ali Rahimiakbar 외

Despite progress in Vision-Language Models (VLMs), their capacity for visual reasoning is often limited by the \textit{binding problem}: the failure to reliably associate perceptual features with their correct visual ref…

Visual Reasoning