Chatting with Images for Introspective Visual Thinking

• URL: http://arxiv.org/abs/2602.11073v2
• Date: Thu, 12 Feb 2026 16:49:33 GMT
• Title: Chatting with Images for Introspective Visual Thinking
• Authors: Junfei Wu, Jian Guan, Qiang Liu, Shu Wu, Liang Wang, Wei Wu, Tieniu Tan,
• Abstract summary: ''Chatting with images'' is a new framework that reframes visual manipulation as language-guided feature modulation.<n>Under the guidance of expressive language prompts, the model dynamically performs joint re-encoding over multiple image regions.<n>ViLaVT achieves strong and consistent improvements on complex multi-image and video-based spatial reasoning tasks.
• Score: 50.7747647794877
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images'' attempts to alleviate this limitation by manipulating images via external tools or code; however, the resulting visual states are often insufficiently grounded in linguistic semantics, impairing effective cross-modal alignment - particularly when visual semantics or geometric relationships must be reasoned over across distant regions or multiple images. To address these challenges, we propose ''chatting with images'', a new framework that reframes visual manipulation as language-guided feature modulation. Under the guidance of expressive language prompts, the model dynamically performs joint re-encoding over multiple image regions, enabling tighter coupling between linguistic reasoning and visual state updates. We instantiate this paradigm in ViLaVT, a novel LVLM equipped with a dynamic vision encoder explicitly designed for such interactive visual reasoning, and trained it with a two-stage curriculum combining supervised fine-tuning and reinforcement learning to promote effective reasoning behaviors. Extensive experiments across eight benchmarks demonstrate that ViLaVT achieves strong and consistent improvements, with particularly pronounced gains on complex multi-image and video-based spatial reasoning tasks.

Related papers

• Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving [61.992824291296444]
  Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs)<n>This paper proposes a paradigm shift: instead of training end-to-end vision-language reasoning models, we advocate for developing a decoupled reasoning framework.
  arXiv  Detail & Related papers  (2025-05-23T08:18:00Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models [24.456117679941816]
  Contrastive Reading Model (Cream) is a novel neural architecture designed to enhance the language-image understanding capability of Large Language Models (LLMs) Our approach bridges the gap between vision and language understanding, paving the way for the development of more sophisticated Document Intelligence Assistants.
  arXiv  Detail & Related papers  (2023-05-24T11:59:13Z)
• Multi-Modal Representation Learning with Text-Driven Soft Masks [48.19806080407593]
  We propose a visual-linguistic representation learning approach within a self-supervised learning framework. We generate diverse features for the image-text matching (ITM) task via soft-masking the regions in an image. We identify the relevant regions to each word by computing the word-conditional visual attention using multi-modal encoder.
  arXiv  Detail & Related papers  (2023-04-03T05:07:49Z)
• Two-stage Visual Cues Enhancement Network for Referring Image Segmentation [89.49412325699537]
  Referring Image (RIS) aims at segmenting the target object from an image referred by one given natural language expression. In this paper, we tackle this problem by devising a Two-stage Visual cues enhancement Network (TV-Net) Through the two-stage enhancement, our proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image.
  arXiv  Detail & Related papers  (2021-10-09T02:53:39Z)
• Improving Image Captioning with Better Use of Captions [65.39641077768488]
  We present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences.
  arXiv  Detail & Related papers  (2020-06-21T14:10:47Z)

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.