Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

• URL: http://arxiv.org/abs/2505.18842v1
• Date: Sat, 24 May 2025 19:30:47 GMT
• Title: Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation
• Authors: Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee, Min Soo Kim, Youngjae Yu,
• Abstract summary: We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs)<n>v1 introduces a simple point-and-copy mechanism that allows the model to dynamically retrieve relevant image regions throughout the reasoning process.<n>Our results suggest that dynamic visual access is a promising direction for enhancing grounded multimodal reasoning.
• Score: 22.27973335431714
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present v1, a lightweight extension to Multimodal Large Language Models (MLLMs) that enables selective visual revisitation during inference. While current MLLMs typically consume visual input only once and reason purely over internal memory, v1 introduces a simple point-and-copy mechanism that allows the model to dynamically retrieve relevant image regions throughout the reasoning process. This mechanism augments existing architectures with minimal modifications, enabling contextual access to visual tokens based on the model's evolving hypotheses. To train this capability, we construct v1g, a dataset of 300K multimodal reasoning traces with interleaved visual grounding annotations. Experiments on three multimodal mathematical reasoning benchmarks -- MathVista, MathVision, and MathVerse -- demonstrate that v1 consistently improves performance over comparable baselines, particularly on tasks requiring fine-grained visual reference and multi-step reasoning. Our results suggest that dynamic visual access is a promising direction for enhancing grounded multimodal reasoning. Code, models, and data will be released to support future research.

Related papers

• 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)
• Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps [56.76175383189738]
  We introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding and spatial reasoning abilities of MLLMs.<n>ReasonMap encompasses high-resolution transit maps from 30 cities across 13 countries and includes 1,008 question-answer pairs spanning two question types and three templates.<n> Comprehensive evaluations of 15 popular MLLMs, including both base and reasoning variants, reveal a counterintuitive pattern.
  arXiv  Detail & Related papers  (2025-05-24T12:33:52Z)
• 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.<n>TVC helps the model retain attention to the visual components throughout the reasoning.<n>Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T16:45:12Z)
• 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.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>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)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models [23.044366104080822]
  We introduce textbfUniRS, the first vision-language model bftextremote bftextsensing tasks across various types of visual input.<n>UniRS supports single images, dual-time image pairs, and videos as input, enabling comprehensive remote sensing temporal analysis.<n> Experimental results show that UniRS achieves state-of-the-art performance across diverse tasks.
  arXiv  Detail & Related papers  (2024-12-30T06:34:18Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation.<n>We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE)<n>DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning [40.972648044298374]
  Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. They often lack interpretability and struggle with complex visual inputs. We introduce the large-scale Visual CoT dataset comprising 438k question-answer pairs. We propose a multi-turn processing pipeline that dynamically focuses on visual inputs and provides interpretable thoughts.
  arXiv  Detail & Related papers  (2024-03-25T17:59:23Z)
• Multi-modal Auto-regressive Modeling via Visual Words [96.25078866446053]
  We propose the concept of visual tokens, which maps the visual features to probability distributions over Large Multi-modal Models' vocabulary. We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.
  arXiv  Detail & Related papers  (2024-03-12T14:58:52Z)

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.