Visual Planning: Let's Think Only with Images

• URL: http://arxiv.org/abs/2505.11409v1
• Date: Fri, 16 May 2025 16:17:22 GMT
• Title: Visual Planning: Let's Think Only with Images
• Authors: Yi Xu, Chengzu Li, Han Zhou, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulić,
• Abstract summary: We argue that language may not always be the most natural or effective modality for reasoning, particularly in tasks involving spatial and geometrical information.<n>Motivated by this, we propose a new paradigm, Visual Planning, which enables planning through purely visual representations, independent of text.<n>In this paradigm, planning is executed via sequences of images that encode step-by-step inference in the visual domain, akin to how humans sketch or visualize future actions.
• Score: 30.67065689757505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have substantially enhanced machine reasoning across diverse tasks. However, these models predominantly rely on pure text as the medium for both expressing and structuring reasoning, even when visual information is present. In this work, we argue that language may not always be the most natural or effective modality for reasoning, particularly in tasks involving spatial and geometrical information. Motivated by this, we propose a new paradigm, Visual Planning, which enables planning through purely visual representations, independent of text. In this paradigm, planning is executed via sequences of images that encode step-by-step inference in the visual domain, akin to how humans sketch or visualize future actions. We introduce a novel reinforcement learning framework, Visual Planning via Reinforcement Learning (VPRL), empowered by GRPO for post-training large vision models, leading to substantial improvements in planning in a selection of representative visual navigation tasks, FrozenLake, Maze, and MiniBehavior. Our visual planning paradigm outperforms all other planning variants that conduct reasoning in the text-only space. Our results establish Visual Planning as a viable and promising alternative to language-based reasoning, opening new avenues for tasks that benefit from intuitive, image-based inference.

Related papers

• Decoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving [57.22004912994658]
  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)
• VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making [21.61801132083334]
  VIPER is a novel framework for multimodal instruction-based planning.<n>It integrates VLM-based perception with LLM-based reasoning.<n>We show that VIPER significantly outperforms state-of-the-art visual instruction-based planners.
  arXiv  Detail & Related papers  (2025-03-19T11:05:42Z)
• Generative Visual Communication in the Era of Vision-Language Models [9.229067992381763]
  In today's visually saturated world, effective design demands an understanding of graphic design principles.<n>This dissertation explores how recent advancements in vision-language models can be leveraged to automate the creation of effective visual communication designs.
  arXiv  Detail & Related papers  (2024-11-27T20:04:31Z)
• Using Left and Right Brains Together: Towards Vision and Language Planning [95.47128850991815]
  We introduce a novel vision-language planning framework to perform concurrent visual and language planning for tasks with inputs of any form. We evaluate the effectiveness of our framework across vision-language tasks, vision-only tasks, and language-only tasks.
  arXiv  Detail & Related papers  (2024-02-16T09:46:20Z)
• EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning [84.6451394629312]
  We introduce EgoPlan-Bench, a benchmark to evaluate the planning abilities of MLLMs in real-world scenarios. We show that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. We also present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench.
  arXiv  Detail & Related papers  (2023-12-11T03:35:58Z)
• Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning [36.131648635051334]
  Visual planning simulates how humans make decisions to achieve desired goals. We propose an interpretable and generalizable visual planning framework. We show that our framework can generalize to unseen task trajectories, unseen object categories, and real-world data.
  arXiv  Detail & Related papers  (2023-10-05T05:41:21Z)
• 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)
• MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action [96.33509740612486]
  MM-REACT is a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. MM-REACT's prompt design allows language models to accept, associate, and process multimodal information.
  arXiv  Detail & Related papers  (2023-03-20T18:31:47Z)
• A Picture is Worth a Thousand Words: Language Models Plan from Pixels [53.85753597586226]
  Planning is an important capability of artificial agents that perform long-horizon tasks in real-world environments. In this work, we explore the use of pre-trained language models (PLMs) to reason about plan sequences from text instructions in embodied visual environments.
  arXiv  Detail & Related papers  (2023-03-16T02:02:18Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)
• Learning Visual Representations with Caption Annotations [19.24013129952071]
  We propose a proxy task to learn visual representations over image-caption pairs. ICMLM consists in predicting masked words in captions by relying on visual cues. Our experiments confirm that image captions can be leveraged to inject global and localized semantic information into visual representations.
  arXiv  Detail & Related papers  (2020-08-04T08:04:16Z)

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.