Thinking with Spatial Code for Physical-World Video Reasoning

• URL: http://arxiv.org/abs/2603.05591v1
• Date: Thu, 05 Mar 2026 19:00:02 GMT
• Title: Thinking with Spatial Code for Physical-World Video Reasoning
• Abstract summary: Thinking with Spatial Code is a framework that transforms RGB video into explicit, temporally coherent 3D representations.<n>We highlight the empirical finding that our proposed spatial encoder can parse videos into structured spatial code with explicit 3D oriented bounding boxes and semantic labels.
• Score: 27.397518169065634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Thinking with Spatial Code, a framework that transforms RGB video into explicit, temporally coherent 3D representations for physical-world visual question answering. We highlight the empirical finding that our proposed spatial encoder can parse videos into structured spatial code with explicit 3D oriented bounding boxes and semantic labels, enabling large language models (LLMs) to reason directly over explicit spatial variables. Specifically, we propose the spatial encoder that encodes image and geometric features by unifying 6D object parsing and tracking backbones with geometric prediction, and we further finetuning LLMs with reinforcement learning using a spatial rubric reward that encourages perspective-aware, geometrically grounded inference. As a result, our model outperforms proprietary vision-language models on VSI-Bench, setting a new state-of-the-art. Code is available at https://github.com/Beckschen/spatialcode.

Related papers

• Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models [32.477423778941386]
  We present GeoVR, a framework that learns geometric representations using purely 2D video sequences.<n>Rather than employing superficial feature mixing, GeoVR reshapes the internal representations of the MLLM by distilling geometry knowledge.<n>Experiments on spatial reasoning benchmarks demonstrate that GeoVR achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-06-04T08:11:12Z)
• Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment [50.02189698630855]
  We propose a Proxy3D method with compact yet comprehensive 3D proxy representations for the vision modality.<n>Our method achieves competitive or state-of-the-art performance in 3D visual question answering, visual grounding and general spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T17:50:47Z)
• Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps [77.63233146945718]
  We introduce Cog3DMap, a framework that recurrently constructs an explicit 3D memory from multi-view images.<n>Our framework enables direct reasoning over a spatially structured 3D map, achieving state-of-the-art performance on various spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-24T10:05:32Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning [43.746951848993035]
  spatial intelligence can emerge from 2D vision alone, rather than being imposed via explicit spatial instruction tuning.<n>We introduce Spa3R, a self-supervised framework that learns a unified view-in spatial representation directly from unposed multi-view images.<n>Experiments demonstrate Spa3-VLM achieves state-of-the-art accuracy of 58.6% on 3D VQA, significantly outperforming prior methods.
  arXiv  Detail & Related papers  (2026-02-24T18:37:34Z)
• UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding [65.60549881706959]
  We introduce UniUGG, the first unified understanding and generation framework for 3D modalities.<n>Our framework employs an LLM to comprehend and decode sentences and 3D representations.<n>We propose a spatial decoder leveraging a latent diffusion model to generate high-quality 3D representations.
  arXiv  Detail & Related papers  (2025-08-16T07:27:31Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• Re-Thinking Inverse Graphics With Large Language Models [51.333105116400205]
  Inverse graphics -- inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. We propose the Inverse-Graphics Large Language Model (IG-LLM), an inversegraphics framework centered around an LLM. We incorporate a frozen pre-trained visual encoder and a continuous numeric head to enable end-to-end training.
  arXiv  Detail & Related papers  (2024-04-23T16:59:02Z)
• Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics [74.6968179473212]
  This paper proposes a novel pretext task to address the self-supervised learning problem. We compute a series of partitioning-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion. A neural network is built and trained to yield the statistical summaries given the video frames as inputs.
  arXiv  Detail & Related papers  (2020-08-31T08:31:56Z)

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.