Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination

• URL: http://arxiv.org/abs/2401.08025v2
• Date: Wed, 21 Feb 2024 22:11:19 GMT
• Title: Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination
• Abstract summary: We leverage a single Vision-Language Model (VLM) to generate a structured representation of the question using HTML, then render the HTML as an image, and finally use the same VLM to answer the question using both the question and the image. We evaluate our approach on three mathematics tasks and nine general-purpose reasoning tasks using state-of-the-art (LLAVA-1.5 and GEMINI PRO) VLMs.
• Score: 40.83905569501714
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The potential of Vision-Language Models (VLMs) often remains underutilized in handling complex text-based problems, particularly when these problems could benefit from visual representation. Resonating with humans' ability to solve complex text-based problems by (1) creating a visual diagram from the problem and (2) deducing what steps they need to take to solve it, we propose Self-Imagine. We leverage a single Vision-Language Model (VLM) to generate a structured representation of the question using HTML, then render the HTML as an image, and finally use the same VLM to answer the question using both the question and the image. Our approach does not require any additional training data or training. We evaluate our approach on three mathematics tasks and nine general-purpose reasoning tasks using state-of-the-art (LLAVA-1.5 and GEMINI PRO) VLMs. Our approach boosts the performance of LLAVA-1.5 and GEMINI PRO on all math tasks (on average GSM8K: +3.1%; ASDIV: +3.2%; SVAMP: +6.9%) and the majority of the general-purpose reasoning tasks by 3.2% to 6.0% on average.

Related papers

• Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency [29.28977802424541]
  We introduce VCBENCH, a benchmark for multimodal mathematical reasoning with explicit visual dependencies.<n> VCBENCH includes 1,720 problems across six cognitive domains, featuring 6,697 images (averaging 3.9 per question) to ensure multi-image reasoning.<n>We evaluate 26 state-of-the-art LVLMs on VCBENCH, revealing substantial performance disparities, with even the top models unable to exceed 50% accuracy.
  arXiv  Detail & Related papers  (2025-04-24T06:16:38Z)
• Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection [53.558449071113245]
  Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM) Recent advancements in vision-language modeling introduce image cropping techniques that feed all encoded sub-images into the model. We propose a lightweight, universal framework that seamlessly integrates with existing VLMs to enhance their ability to process finegrained details.
  arXiv  Detail & Related papers  (2025-03-14T18:33:31Z)
• MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions [37.60935581067836]
  MindGYM is a framework that enhances large vision-language models (VLMs) through synthetic self-challenging questions. MindGYM achieves high data efficiency (e.g., +16% gains on MathVision-Mini with only 400 samples), computational efficiency (reducing both training and inference costs), and robust generalization across tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:03:03Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning. We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Probing Visual Language Priors in VLMs [51.016683265437536]
  We introduce ViLP, a benchmark featuring deliberately out-of-distribution images. Each question in ViLP is coupled with three potential answers and three corresponding images. We propose a self-improving framework in which models generate new VQA data, then apply pixel-level and semantic corruptions to form "good-bad" image pairs for self-training.
  arXiv  Detail & Related papers  (2024-12-31T17:54:29Z)
• DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models [19.787224412654872]
  We introduce DynaMath, a dynamic visual math benchmark designed for in-depth assessment of Vision-Language Models (VLMs) DynaMath includes 501 high-quality, multi-topic seed questions, each represented as a Python program. Our results show that the worst-case model accuracy, defined as the percentage of correctly answered seed questions in all 10 variants, is significantly lower than the average-case accuracy.
  arXiv  Detail & Related papers  (2024-10-29T17:29:19Z)
• AutoBench-V: Can Large Vision-Language Models Benchmark Themselves? [55.14033256706175]
  Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. We introduce AutoBench-V, an automated framework for serving evaluation on demand. Through an extensive evaluation of seven popular LVLMs across five demanded user inputs, the framework shows effectiveness and reliability.
  arXiv  Detail & Related papers  (2024-10-28T17:55:08Z)
• Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning [5.9767694994869425]
  Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems. They struggle with mathematical diagrams since they are primarily trained on natural scene images. We propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment.
  arXiv  Detail & Related papers  (2024-08-16T10:11:05Z)
• AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding [44.79843213164787]
  Embodied AI personal assistants require embodied understanding to collaborate with humans effectively. Current Vision-Language Models (VLMs) primarily focus on third-person view videos, neglecting the richness of egocentric experience. We introduce the Egocentric Video Understanding dataset (EVUD) for training VLMs on video captioning and question answering tasks specific to egocentric videos. We present AlanaVLM, a 7B parameter VLM trained using parameter-efficient methods on EVUD.
  arXiv  Detail & Related papers  (2024-06-19T20:14:14Z)
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? [99.0305256706604]
  We introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning.
  arXiv  Detail & Related papers  (2024-03-21T17:59:50Z)
• Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models [73.40350756742231]
  Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored.
  arXiv  Detail & Related papers  (2024-02-12T18:21:14Z)
• CogCoM: Train Large Vision-Language Models Diving into Details through Chain of Manipulations [61.21923643289266]
  Chain of Manipulations is a mechanism that enables Vision-Language Models to solve problems step-by-step with evidence. After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) actively without involving external tools. Our trained model, textbfCogCoM, achieves state-of-the-art performance across 9 benchmarks from 4 categories.
  arXiv  Detail & Related papers  (2024-02-06T18:43:48Z)
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts [170.01089233942594]
  MathVista is a benchmark designed to combine challenges from diverse mathematical and visual tasks. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning.
  arXiv  Detail & Related papers  (2023-10-03T17:57:24Z)
• Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering [17.51860125438028]
  We propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. Our results on a visual question answering task which requires external knowledge (OK-VQA) show that our text-only model outperforms pretrained multimodal (image-text) models of comparable number of parameters.
  arXiv  Detail & Related papers  (2021-09-15T14:11:29Z)

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.