PRISM: Progressive Reasoning through Iterative Slot Memory for Vision

• URL: http://arxiv.org/abs/2605.30942v1
• Date: Fri, 29 May 2026 07:29:30 GMT
• Title: PRISM: Progressive Reasoning through Iterative Slot Memory for Vision
• Abstract summary: 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.
• Score: 12.631034298090908
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete observations. Inspired by the iterative nature of human perception, we introduce PRISM (Progressive Reasoning through Iterative Slot Memory), a pyramid vision architecture that reasons over images through iterative refinement. 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. This organize-recall-refine process operates recurrently across multiple scales, enabling progressive improvement of visual representations. Across standard vision tasks, including image classification, object detection, and semantic segmentation, PRISM achieves competitive performance while demonstrating improved robustness under incomplete observations such as occlusion. These results suggest that iterative reasoning with structured representations and memory is a promising direction for building more resilient and adaptive vision models. Source code and models will be released.

Related papers

• Probing Visual Planning in Image Editing Models [9.427970566064213]
  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.
  arXiv  Detail & Related papers  (2026-04-23T19:00:31Z)
• How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing [56.60465182650588]
  We introduce three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning.<n>We propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment.<n>We find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models.
  arXiv  Detail & Related papers  (2026-02-02T09:24:45Z)
• 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)
• TokBench: Evaluating Your Visual Tokenizer before Visual Generation [75.38270351179018]
  We analyze text and face reconstruction quality across various scales for different image tokenizers and VAEs.<n>Our results show modern visual tokenizers still struggle to preserve fine-grained features, especially at smaller scales.
  arXiv  Detail & Related papers  (2025-05-23T17:52:16Z)
• End-to-End Vision Tokenizer Tuning [73.3065542220568]
  The vision tokenizer optimized for low-level reconstruction is to downstream tasks requiring varied representations and semantics.<n>The loss of the vision tokenization can be the representation bottleneck for target tasks.<n>We propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks.
  arXiv  Detail & Related papers  (2025-05-15T17:59:39Z)
• From Visual Explanations to Counterfactual Explanations with Latent Diffusion [11.433402357922414]
  We propose a new approach to tackle two key challenges in recent prominent works.<n>First, we determine which specific counterfactual features are crucial for distinguishing the "concept" of the target class from the original class.<n>Second, we provide valuable explanations for the non-robust classifier without relying on the support of an adversarially robust model.
  arXiv  Detail & Related papers  (2025-04-12T13:04:00Z)
• Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases [69.46487306858789]
  Conditional Autoregressive Slot Attention (CA-SA) is a framework that enhances the temporal consistency of extracted object-centric representations in video-centric vision tasks. We present qualitative and quantitative results showing that our proposed method outperforms the considered baselines on downstream tasks.
  arXiv  Detail & Related papers  (2024-10-21T07:44:44Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Top-Down Visual Attention from Analysis by Synthesis [87.47527557366593]
  We consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. We propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and controllable achieves top-down attention.
  arXiv  Detail & Related papers  (2023-03-23T05:17:05Z)
• 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)
• Understanding invariance via feedforward inversion of discriminatively trained classifiers [30.23199531528357]
  Past research has discovered that some extraneous visual detail remains in the output logits. We develop a feedforward inversion model that produces remarkably high fidelity reconstructions. Our approach is based on BigGAN, with conditioning on logits instead of one-hot class labels.
  arXiv  Detail & Related papers  (2021-03-15T17:56:06Z)

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.