Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models

• URL: http://arxiv.org/abs/2411.18142v3
• Date: Wed, 11 Jun 2025 02:49:11 GMT
• Title: Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models
• Authors: Jingming Liu, Yumeng Li, Boyuan Xiao, Yichang Jian, Ziang Qin, Tianjia Shao, Yao-Xiang Ding, Kun Zhou,
• Abstract summary: Multimodal Large Language Models (MLLMs) struggle with some seemingly straightforward visual tasks.<n>We argue that these tasks challenge the ability of visual-to-textual conversion.<n>We propose an approach, autonomous imagination, to enable MLLMs to iteratively modify visual inputs.
• Score: 27.78471707423076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Under pure textual modality, Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning tasks by decomposing them into simpler sub-problems. However, Multimodal Large Language Models (MLLMs) still struggle with some seemingly straightforward visual tasks, such as counting and solving jigsaw puzzles. We argue that these tasks challenge the ability of visual-to-textual conversion, where MLLMs convert visual information perceived from the input scene, to textual information for further reasoning and generating the answer. If the complexity of the visual input is beyond the perceptual capability of the MLLMs, without decomposing this conversion process, simply scaling inference-time reasoning cannot solve the task because it repeatedly encounters the same perceptual bottleneck. We propose an approach, autonomous imagination, to enable MLLMs to iteratively modify visual inputs (e.g. isolating objects, rearranging puzzle pieces) into intermediate visual states, decomposing visual-to-textual conversion into closed-loop visual modification steps. We show that, without any retraining, MLLMs can now solve tasks initially beyond their perceptual capability, highlighting that closed-loop visual modification can be an effective way of decomposing the visual reasoning task into solvable substeps. Project page: https://future-item.github.io/autoimagine-site/

Related papers

• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning [20.632248864242968]
  We show that language-only models can achieve comparable or even better performance than MLLMs that consume raw visual inputs.<n>Motivated by this, we propose a simple visual perturbation framework that enhances perceptual robustness without requiring algorithmic modifications.<n>Our findings highlight the critical role of visual perturbation in multimodal mathematical reasoning.
  arXiv  Detail & Related papers  (2025-06-11T13:39:46Z)
• Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification [22.871255950998016]
  We introduce a novel framework for inference-time visual tokens scaling that enables MLLMs to perform verifier-guided reasoning over visual content.<n>Our method significantly outperforms existing approaches across diverse visual reasoning benchmarks.<n>These results demonstrate the promise of dynamic inference mechanisms for enabling fine-grained, context-aware visual reasoning in next-generation MLLMs.
  arXiv  Detail & Related papers  (2025-06-08T17:38:49Z)
• How Can Objects Help Video-Language Understanding? [16.63183488540909]
  We introduce ObjectML, a framework capable of leveraging arbitrary computer vision algorithm to extract and structured visual representation.<n>Through extensive evaluations on six video question benchmarks, we confirm that explicit integration of object-centric representation remains necessary.<n>Surprisingly, we observe that the simple approach quantizing the continuous, structured object information and representing them as plain text performs the best.
  arXiv  Detail & Related papers  (2025-04-10T04:59:28Z)
• Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning [53.790502697674754]
  We propose Take-along Visual Conditioning (TVC), a strategy that shifts image input to critical reasoning stages. TVC helps the model retain attention to the visual components throughout the reasoning. Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T16:45:12Z)
• Grounded Chain-of-Thought for Multimodal Large Language Models [66.04061083611863]
  We propose a new learning task for multimodal large language models (MLLMs) called Grounded Chain-of-Thought (GCoT) GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis. To facilitate this task, we also carefully design and construct a dataset called multimodal grounded chain-of-thought (MM-GCoT) consisting of 24,022 GCoT examples for 5,033 images.
  arXiv  Detail & Related papers  (2025-03-17T04:07:47Z)
• How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game [11.721839449847472]
  We introduce MM-Escape, a benchmark for investigating multimodal reasoning. MM-Escape emphasizes intermediate model behaviors alongside final task completion. Extensive experiments show that MLLMs, regardless of scale, can successfully complete the simplest room escape tasks. We observe that performance bottlenecks vary across models, revealing distinct failure modes and limitations in their multimodal reasoning abilities.
  arXiv  Detail & Related papers  (2025-03-13T04:48:43Z)
• Imagine while Reasoning in Space: Multimodal Visualization-of-Thought [70.74453180101365]
  Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) We propose a new reasoning paradigm, Multimodal Visualization-of-Thought (MVoT) It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces.
  arXiv  Detail & Related papers  (2025-01-13T18:23:57Z)
• Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild [35.91285472401222]
  We devise an innovative training and reasoning framework suitable for lightweight Multimodal Large Language Models (MLLMs) Our self-questioning approach organically guides MLLMs to focus on visual clues relevant to the target problem, reducing hallucinations and enhancing the model's ability to describe fine-grained image details. Our experiments on various benchmarks demonstrate SQ's remarkable capabilities in self-questioning, zero-shot visual reasoning and hallucination mitigation.
  arXiv  Detail & Related papers  (2025-01-06T12:16:56Z)
• Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning [151.4060202671114]
  multimodal large language models (MLLMs) have shown unprecedented capabilities in advancing vision-language tasks.<n>This paper introduces a novel bottom-up reasoning framework to address hallucinations in MLLMs.<n>Our framework systematically addresses potential issues in both visual and textual inputs by verifying and integrating perception-level information with cognition-level commonsense knowledge.
  arXiv  Detail & Related papers  (2024-12-15T09:10:46Z)
• Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination [13.706325901731665]
  Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs) But their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension.
  arXiv  Detail & Related papers  (2024-11-15T21:01:37Z)
• TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning [54.033346088090674]
  We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability. To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• Enhancing Advanced Visual Reasoning Ability of Large Language Models [20.32900494896848]
  Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning. We propose Complex Visual Reasoning Large Language Models (CVR-LLM) Our approach transforms images into detailed, context-aware descriptions using an iterative self-refinement loop. We also introduce a novel multi-modal in-context learning (ICL) methodology to enhance LLMs' contextual understanding and reasoning.
  arXiv  Detail & Related papers  (2024-09-21T02:10:19Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language.<n>This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok)<n>SeTok groups visual features into semantic units via a dynamic clustering algorithm.<n>The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Auto-Encoding Morph-Tokens for Multimodal LLM [151.2618346912529]
  We propose encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts. Experiments show that morph-tokens can achieve a new SOTA for multimodal comprehension and generation simultaneously.
  arXiv  Detail & Related papers  (2024-05-03T08:43:06Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)
• DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent) [73.10899129264375]
  This paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Given a video with a question/task, DoraemonGPT begins by converting the input video into a symbolic memory that stores task-related attributes. We extensively evaluate DoraemonGPT's effectiveness on three benchmarks and several in-the-wild scenarios.
  arXiv  Detail & Related papers  (2024-01-16T14:33:09Z)
• Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs [50.77984109941538]
  Our research reveals that the visual capabilities in recent multimodal LLMs still exhibit systematic shortcomings. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. We evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs.
  arXiv  Detail & Related papers  (2024-01-11T18:58:36Z)
• Frozen Transformers in Language Models Are Effective Visual Encoder Layers [26.759544759745648]
  Large language models (LLMs) are surprisingly strong encoders for purely visual tasks in the absence of language. Our work pushes the boundaries of leveraging LLMs for computer vision tasks. We propose the information filtering hypothesis to explain the effectiveness of pre-trained LLMs in visual encoding.
  arXiv  Detail & Related papers  (2023-10-19T17:59:05Z)

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.