UniVR: Thinking in Visual Space for Unified Visual Reasoning

• URL: http://arxiv.org/abs/2607.12800v1
• Date: Tue, 14 Jul 2026 14:15:13 GMT
• Title: UniVR: Thinking in Visual Space for Unified Visual Reasoning
• Abstract summary: We introduce UniVR, the first investigation into simultaneously learning complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations.<n>At its core, UniVR features VR-GRPO, a reinforcement learning paradigm with complementary global and step-level rewards.<n>To train and evaluate UniVR, we construct VR-X, a large-scale benchmark curated from 16 diverse sources spanning long-horizon manipulation, spatial puzzles, and physical reasoning.
• Score: 109.8746743219571
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning broad world knowledge directly from raw visual data is a fundamental capability of intelligence. We introduce UniVR, the first investigation into simultaneously learning complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations. At its core, UniVR features VR-GRPO, a reinforcement learning paradigm with complementary global and step-level rewards. This approach enforces logical coherence and physical consistency throughout the reasoning process without requiring task-specific heuristics or image-text pairs. To train and evaluate UniVR, we construct VR-X, a large-scale benchmark curated from 16 diverse sources spanning long-horizon manipulation, spatial puzzles, and physical reasoning. It is the first comprehensive suite to assess these heterogeneous capabilities under a purely visual protocol. Remarkably, UniVR achieves up to a 25% improvement on VR-X, and its superior visual reasoning also boosts performance on various multimodal understanding benchmarks. These findings underscore the vast potential of reasoning within visual spaces, with all code, data, and models are open-sourced for further research.

Related papers

• PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments [36.84821207878773]
  Visual reasoning in multimodal large language models (MLLMs) has primarily been studied in static, fully observable settings.<n>We introduce the Active Visual Reasoning (AVR) task, extending visual reasoning to partially observable, interactive environments.<n>We present a benchmark featuring multi-round interactive environments designed to assess both reasoning and information-gathering efficiency.
  arXiv  Detail & Related papers  (2025-10-24T02:59:00Z)
• How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective [103.44502230776352]
  We present a systematic investigation of Visual Spatial Reasoning (VSR) in Vision-Language Models (VLMs)<n>We categorize spatial intelligence into three levels of capability, ie, basic perception, spatial understanding, spatial planning, and curate SIBench, a spatial intelligence benchmark encompassing nearly 20 open-source datasets across 23 task settings.
  arXiv  Detail & Related papers  (2025-09-23T12:00:14Z)
• Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning [52.107043437362556]
  Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios.<n>This paper proposes a novel Unified Conditional Generative Solver (UCGS) to address multiple tasks in a unified framework.<n>UCGS exhibits the ability of zero-shot reasoning, enabling it to perform abstract reasoning on problems from unseen tasks in the testing phase.
  arXiv  Detail & Related papers  (2025-07-15T21:54:51Z)
• ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos [71.62145804686062]
  Assessing the quality of experience (QoE) of egocentric spatial videos is crucial to ensure a high-quality viewing experience.<n>We introduce the first Egocentric Spatial Video Quality Assessment Database (ESVQAD), which comprises 600 egocentric spatial videos.<n>We also propose a novel multi-dimensional binocular feature fusion model, termed ESVQAnet, which integrates binocular spatial, motion, and semantic features to predict the overall perceptual quality.
  arXiv  Detail & Related papers  (2024-12-29T10:13:30Z)
• A Unified View of Abstract Visual Reasoning Problems [0.0]
  We introduce a unified view of tasks, where each instance is rendered as a single image with no priori assumptions about the number of panels, their location, or role. The main advantage of the proposed unified view is the ability to develop universal learning models applicable to various tasks. Experiments conducted on four datasets with Raven's Progressive Matrices and Visual Analogy Problems show that the proposed unified representation of tasks poses a challenge to state-of-the-art Deep Learning (DL) models and, more broadly, contemporary DL image recognition methods.
  arXiv  Detail & Related papers  (2024-06-16T20:52:44Z)
• Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? [106.81451807227103]
  We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual 'foundation models' for Embodied AI. To study the effect of pre-training data size and diversity, we combine over 4,000 hours of egocentric videos from 7 different sources. Our largest model, named VC-1, outperforms all prior PVRs on average but does not universally dominate either.
  arXiv  Detail & Related papers  (2023-03-31T17:56:33Z)
• See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning [60.43585179885355]
  We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. We conduct experiments on a range of knowledge-based visual reasoning datasets.
  arXiv  Detail & Related papers  (2023-01-12T18:59:50Z)
• Facial Expression Recognition Under Partial Occlusion from Virtual Reality Headsets based on Transfer Learning [0.0]
  convolutional neural network based approaches has become widely adopted due to their proven applicability to Facial Expression Recognition task. However, recognizing facial expression while wearing a head-mounted VR headset is a challenging task due to the upper half of the face being completely occluded. We propose a geometric model to simulate occlusion resulting from a Samsung Gear VR headset that can be applied to existing FER datasets.
  arXiv  Detail & Related papers  (2020-08-12T20:25:07Z)

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.