Probing Visual Planning in Image Editing Models

• URL: http://arxiv.org/abs/2604.22868v1
• Date: Thu, 23 Apr 2026 19:00:31 GMT
• Title: Probing Visual Planning in Image Editing Models
• Abstract summary: We present EAR, an editing-as-reasoning paradigm that reformulates visual planning as a single-step image transformation.<n>To isolate intrinsic reasoning from visual recognition, we employ abstract puzzles as probing tasks.
• Score: 9.427970566064213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in machine learning, this inherently visual problem is often tackled through a verbal-centric lens. While recent research demonstrates the promise of fully visual approaches, they suffer from significant computational inefficiency due to the step-by-step planning-by-generation paradigm. In this work, we present EAR, an editing-as-reasoning paradigm that reformulates visual planning as a single-step image transformation. To isolate intrinsic reasoning from visual recognition, we employ abstract puzzles as probing tasks and introduce AMAZE, a procedurally generated dataset that features the classical Maze and Queen problems, covering distinct, complementary forms of visual planning. The abstract nature of AMAZE also facilitates automatic evaluation of autoregressive and diffusion-based models in terms of both pixel-wise fidelity and logical validity. We assess leading proprietary and open-source editing models. The results show that they all struggle in the zero-shot setting, finetuning on basic scales enables remarkable generalization to larger in-domain scales and out-of-domain scales and geometries. However, our best model that runs on high-end hardware fails to match the zero-shot efficiency of human solvers, highlighting a persistent gap in neural visual reasoning.

Related papers

• PRISM: Progressive Reasoning through Iterative Slot Memory for Vision [12.631034298090908]
  We introduce PRISM, a pyramid vision architecture that reasons over images through iterative refinement.<n>At a high level, PRISM groups visual features into object-centric representations, retrieves relevant patterns from a learned memory, and iteratively refines the representation to resolve ambiguity and recover missing information.
  arXiv  Detail & Related papers  (2026-05-29T07:29:30Z)
• VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions [51.41587958253802]
  We introduce VISion On Request (VISOR), a method that reduces inference cost without discarding visual information.<n>VISOR improves efficiency by sparsifying the interaction between image and text tokens.<n>Experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results.
  arXiv  Detail & Related papers  (2026-03-24T17:58:17Z)
• A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps [0.9332987715848716]
  We draw inspiration from the human visual system to create smarter image processing models.<n>Using DINO, a self-supervised Vision Transformer, we explore a saccade inspired method to focus the processing of information on key regions in visual space.<n>This selective-processing strategy preserves most of the full-image classification performance and can even outperform it in certain cases.
  arXiv  Detail & Related papers  (2026-03-10T12:54:55Z)
• MentisOculi: Revealing the Limits of Reasoning with Mental Imagery [63.285794947638614]
  We develop MentisOculi, a suite of multi-step reasoning problems amenable to visual solution.<n> evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance.<n>Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning.
  arXiv  Detail & Related papers  (2026-02-02T18:49:06Z)
• 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)
• Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations [61.235500325327585]
  Existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation.<n>We introduce STARE, a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through visual simulation.<n>Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks.
  arXiv  Detail & Related papers  (2025-06-05T05:09:46Z)
• Solving the Clustering Reasoning Problems by Modeling a Deep-Learning-Based Probabilistic Model [1.7955614278088239]
  We introduce PMoC, a deep-learning-based probabilistic model, achieving high reasoning accuracy in the Bongard-Logo.<n>PMoC revitalizes the probabilistic approach, which has been relatively weak in visual abstract reasoning.
  arXiv  Detail & Related papers  (2024-03-05T18:08:29Z)
• 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)
• Look, Remember and Reason: Grounded reasoning in videos with language models [5.3445140425713245]
  Multi-temporal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. We propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, tracking, to endow the model with the required low-level visual capabilities. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, Something-Else and STAR datasets.
  arXiv  Detail & Related papers  (2023-06-30T16:31:14Z)
• GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images [79.39247661907397]
  We introduce an effective framework Generalizable Model-based Neural Radiance Fields to synthesize free-viewpoint images. Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy.
  arXiv  Detail & Related papers  (2023-03-24T03:32:02Z)
• Tuning computer vision models with task rewards [88.45787930908102]
  Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. In natural language processing, this is often addressed using reinforcement learning techniques that align models with a task reward. We adopt this approach and show its surprising effectiveness across multiple computer vision tasks, such as object detection, panoptic segmentation, colorization and image captioning.
  arXiv  Detail & Related papers  (2023-02-16T11:49:48Z)
• Reconstruction-guided attention improves the robustness and shape processing of neural networks [5.156484100374057]
  We build an iterative encoder-decoder network that generates an object reconstruction and uses it as top-down attentional feedback. Our model shows strong generalization performance against various image perturbations. Our study shows that modeling reconstruction-based feedback endows AI systems with a powerful attention mechanism.
  arXiv  Detail & Related papers  (2022-09-27T18:32:22Z)

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.