Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs

• URL: http://arxiv.org/abs/2501.06430v1
• Date: Sat, 11 Jan 2025 04:08:44 GMT
• Title: Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs
• Authors: Shan Zhang, Aotian Chen, Yanpeng Sun, Jindong Gu, Yi-Yu Zheng, Piotr Koniusz, Kai Zou, Anton van den Hengel, Yuan Xue,
• Abstract summary: Current large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. In this paper, we evaluate the visual grounding capabilities of state-of-the-art MLLMs and reveal a significant negative correlation between visual grounding accuracy and problem-solving performance. We propose a novel approach, SVE-Math, featuring a geometric-grounded vision encoder and a feature router that dynamically adjusts the contribution of hierarchical visual feature maps.
• Score: 62.875934732547435
• License:
• Abstract: Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric primitives during image-level contrastive pre-training (e.g., CLIP). While recent efforts to improve math MLLMs have focused on scaling up mathematical visual instruction datasets and employing stronger LLM backbones, they often overlook persistent errors in visual recognition. In this paper, we systematically evaluate the visual grounding capabilities of state-of-the-art MLLMs and reveal a significant negative correlation between visual grounding accuracy and problem-solving performance, underscoring the critical role of fine-grained visual understanding. Notably, advanced models like GPT-4o exhibit a 70% error rate when identifying geometric entities, highlighting that this remains a key bottleneck in visual mathematical reasoning. To address this, we propose a novel approach, SVE-Math (Selective Vision-Enhanced Mathematical MLLM), featuring a geometric-grounded vision encoder and a feature router that dynamically adjusts the contribution of hierarchical visual feature maps. Our model recognizes accurate visual primitives and generates precise visual prompts tailored to the language model's reasoning needs. In experiments, SVE-Math-Qwen2.5-7B outperforms other 7B models by 15% on MathVerse and is compatible with GPT-4V on MathVista. Despite being trained on smaller datasets, SVE-Math-7B achieves competitive performance on GeoQA, rivaling models trained on significantly larger datasets. Our findings emphasize the importance of incorporating fine-grained visual understanding into MLLMs and provide a promising direction for future research.

Related papers

• Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding [94.64781599202882]
  Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks. They often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison. We propose CogAlign, a novel post-training strategy inspired by Piaget's theory of cognitive development.
  arXiv  Detail & Related papers  (2025-02-17T06:54:49Z)
• Distill Visual Chart Reasoning Ability from LLMs to MLLMs [38.62832112530892]
  Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs) We propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and easily scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. We employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs.
  arXiv  Detail & Related papers  (2024-10-24T14:50:42Z)
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders [89.38717274524681]
  This study explores the design space for multimodal large language models (MLLMs) using a mixture of vision encoders and resolutions. Our findings reveal several underlying principles common to various existing strategies, leading to a streamlined yet effective design approach. The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.
  arXiv  Detail & Related papers  (2024-08-28T17:59:31Z)
• MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine [85.80851893886161]
  We propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We use MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B.
  arXiv  Detail & Related papers  (2024-07-11T17:59:47Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training [24.989732666940153]
  Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs. MLLMs still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and Gemini-Pro. We propose a two-step training pipeline VCAR, which emphasizes the Visual Reasoning training in addition to mathematical learning.
  arXiv  Detail & Related papers  (2024-04-22T21:59:35Z)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)
• What Makes for Good Visual Tokenizers for Large Language Models? [26.488269091290597]
  We investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs) We discuss different visual tokenizers pre-trained with dominant methods (i.e., DeiT, CLIP, MAE, DINO) We obtain a new MLLM equipped with a tailored Good Visual Tokenizer (GVT), which exhibits strong visual comprehension capability at multiple scales.
  arXiv  Detail & Related papers  (2023-05-20T16:11:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.