spatial-reasoning

Compose multimodal datasets 🎹

[Awesome-Spatial-VLMs] This repository is the official, community-maintained resource for the survey paper: Spatial Intelligence in Vision-Language Models: A Comprehensive Survey;

[ECCV 2026] Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"

[NeurIPS 2025] Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"

[ECCV 2026] Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

[ICLR 2026] OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

[CVPR 2026 Highlight] SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence

[ECCV 2026] Official implementation of "RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics"

Code for "ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing"

[NeurIPS'24] SpatialEval: a benchmark to evaluate spatial reasoning abilities of MLLMs and LLMs

[ICLR2026] Spatial Reasoning with Vision-Language Models

Helix-AGI is an Agentic AI System that uses a spatial-graph memory retrieval system. Agents receive a rolling adaptive system prompt of memories and skills that afford the agent a highly dynamic center of conceptual gravity. By avoiding long identity files and subagent-heavy workflows, Agents can develop continuously without spiraling costs.

[CVPR2020] A Dataset for SPAtial REasoning on Three-View Line Drawings

PanoWorld: pano-native spatial supersensing for 360° panorama understanding, spatial reasoning, and navigation.

Spatial Aptitude Training for Multimodal Langauge Models

[AAAI 2022] Dataset and pytorch codes for the paper titled "StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts" in AAAI 2022 (Oral)

[ICLR 26] pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning