CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation

• URL: http://arxiv.org/abs/2503.05255v1
• Date: Fri, 07 Mar 2025 09:13:17 GMT
• Title: CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
• Abstract summary: We propose a multi-step reasoning framework that mimics human-like "slow thinking" for multi-image understanding.<n>The construction of interleaved multimodal multi-step reasoning chains, which utilize critical visual region tokens, as supervisory signals.<n>The introduction of a test-time memory augmentation module that expands the model reasoning capacity during inference.
• Score: 12.008690947774015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While previous multimodal slow-thinking methods have demonstrated remarkable success in single-image understanding scenarios, their effectiveness becomes fundamentally constrained when extended to more complex multi-image comprehension tasks. This limitation stems from their predominant reliance on text-based intermediate reasoning processes. While for human, when engaging in sophisticated multi-image analysis, they typically perform two complementary cognitive operations: (1) continuous cross-image visual comparison through region-of-interest matching, and (2) dynamic memorization of critical visual concepts throughout the reasoning chain. Motivated by these observations, we propose the Complex Multi-Modal Chain-of-Thought (CMMCoT) framework, a multi-step reasoning framework that mimics human-like "slow thinking" for multi-image understanding. Our approach incorporates two key innovations: 1. The construction of interleaved multimodal multi-step reasoning chains, which utilize critical visual region tokens, extracted from intermediate reasoning steps, as supervisory signals. This mechanism not only facilitates comprehensive cross-modal understanding but also enhances model interpretability. 2. The introduction of a test-time memory augmentation module that expands the model reasoning capacity during inference while preserving parameter efficiency. Furthermore, to facilitate research in this direction, we have curated a novel multi-image slow-thinking dataset. Extensive experiments demonstrate the effectiveness of our model.

Related papers

• Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning [82.86343313807158]
  We argue that a central challenge is how and when visual evidence is introduced into the reasoning process.<n>Motivated by this insight, we propose CSMR, a multimodal reasoning framework in which a language model controls the reasoning process.
  arXiv  Detail & Related papers  (2026-05-27T08:43:13Z)
• ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion [14.791563751107502]
  ITO is a framework addressing the limitation through two synergistic mechanisms.<n>We show that ITO consistently outperforms strong baselines across classification, retrieval, and multimodal benchmarks.<n>Our analysis reveals that while multiple alignment drives discriminative power, training-time fusion acts as a critical structural regularizer.
  arXiv  Detail & Related papers  (2026-03-03T09:08:53Z)
• Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space [46.05748768260013]
  We propose a test-time Dynamic Multimodal Latent Reasoning framework.<n>It employs confidence-guided latent policy gradient optimization to latent think tokens for in-depth reasoning.<n> Experiments across seven multimodal reasoning benchmarks and various model architectures demonstrate that DMLR significantly improves reasoning and perception performance.
  arXiv  Detail & Related papers  (2025-12-14T10:07:45Z)
• V-Thinker: Interactive Thinking with Images [22.55079103487787]
  Recent advances in vision-centric reasoning explore a promising "Thinking with Images" paradigm for Large Multimodal Models (LMMs)<n>We present V-Thinker, a general-purpose multimodal reasoning assistant that enables interactive, vision-centric thinking through end-to-end reinforcement learning.<n>V-Thinker consistently outperforms strong LMM-based baselines in both general and interactive reasoning scenarios.
  arXiv  Detail & Related papers  (2025-11-06T15:32:29Z)
• QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models [50.51641024244313]
  We investigate how current prompting methods perceive fine-grained visual details and process visual information when dealing with multiple images.<n>Inspired by the findings, we propose a new zero-shot prompting method, Question-Guided Chain-of-Captions (QG-CoC)<n>We evaluate our method on various open-source and closed-source MLLMs for multi-image and single-image benchmarks.
  arXiv  Detail & Related papers  (2025-11-05T05:49:48Z)
• ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning [76.95203056566191]
  Multimodal reasoning requires iterative coordination between language and vision, yet it remains unclear what constitutes a meaningful interleaved chain of thought.<n>We build ThinkMorph, a unified model fine-tuned on approximately 24K high-quality interleaved reasoning traces spanning tasks with varying visual engagement.<n>ThinkMorph learns to generate progressive text-image reasoning steps that concretely manipulate visual content while maintaining coherent verbal logic.
  arXiv  Detail & Related papers  (2025-10-30T17:51:38Z)
• Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers [90.4459196223986]
  A similar evolution is now unfolding in AI, marking a paradigm shift from models that merely think about images to those that can truly think with images.<n>This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace.
  arXiv  Detail & Related papers  (2025-06-30T14:48:35Z)
• PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning [50.21619363035618]
  We propose a general reinforcement learning approach PeRL tailored for interleaved multimodal tasks.<n>We introduce permutation of image sequences to simulate varied positional relationships to explore more spatial and positional diversity.<n>Our experiments confirm that PeRL trained model consistently surpasses R1-related and interleaved VLM baselines by a large margin.
  arXiv  Detail & Related papers  (2025-06-17T18:25:56Z)
• Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought [72.93910800095757]
  multimodal chain-of-thought (MCoT) improves performance and interpretability of large vision-language models (LVLMs)<n>We show that MCoT boosts LVLMs by incorporating visual thoughts, which convey image information to the reasoning process regardless of the MCoT format.<n>We also explore the internal nature of visual thoughts, finding that visual thoughts serve as intermediaries between the input image and reasoning to deeper transformer layers.
  arXiv  Detail & Related papers  (2025-05-21T13:29:58Z)
• Enhancing Multi-hop Reasoning in Vision-Language Models via Self-Distillation with Multi-Prompt Ensembling [11.462550020102935]
  Multi-modal large language models can leverage chain-of-thought prompting for zero or few-shot learning.<n>Similar prompting strategies are less effective for multi-modal LLMs due to modality gaps and task complexity.<n>We propose a self-distillation framework such that the model can improve itself without any annotated data.
  arXiv  Detail & Related papers  (2025-03-03T17:24:42Z)
• Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study [44.35454088618666]
  We investigate popular sampling-based and tree search-based inference-time scaling methods on 10 challenging tasks spanning various domains.<n>Results show that multi-modal thought promotes better performance against conventional text-only thought.<n>Despite these advantages, multi-modal thoughts necessitate higher token consumption for processing richer visual inputs.
  arXiv  Detail & Related papers  (2025-02-17T07:29:01Z)
• 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)<n>We propose a new reasoning paradigm, Multimodal Visualization-of-Thought (MVoT)<n>It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces.
  arXiv  Detail & Related papers  (2025-01-13T18:23:57Z)
• Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering [53.39158264785098]
  Long-term Video Question Answering (VideoQA) is a challenging vision-and-language bridging task. We present an entirely end-to-end solution for VideoQA: Multi-granularity Contrastive cross-modal collaborative Generation model.
  arXiv  Detail & Related papers  (2024-10-12T06:21:58Z)
• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model [49.931663904599205]
  MaVEn is an innovative framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. We show that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.
  arXiv  Detail & Related papers  (2024-08-22T11:57:16Z)
• Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations [19.731611716111566]
  We propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations. We introduce a predictive self-attention module to capture reliable context dynamics within modalities. A hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities. A double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner.
  arXiv  Detail & Related papers  (2024-07-06T04:36:48Z)
• 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)
• Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning [45.517215214938844]
  Chain-of-thought technique has been received well in multi-modal tasks. We propose a novel Aggregation-Graph-of-Thought (AGoT) mechanism for soft-prompt tuning in multi-modal representation learning.
  arXiv  Detail & Related papers  (2024-04-06T07:39:44Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis [19.07020276666615]
  We propose a novel framework named MultiModal Contrastive Learning (MMCL) for multimodal representation to capture intra- and inter-modality dynamics simultaneously. We also design two contrastive learning tasks, instance- and sentiment-based contrastive learning, to promote the process of prediction and learn more interactive information related to sentiment.
  arXiv  Detail & Related papers  (2022-10-26T08:24:15Z)

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.