Compose multimodal datasets 🎹
-
Updated
Jun 6, 2025 - Python
Compose multimodal datasets 🎹
[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"
[CVPR2020] A Dataset for SPAtial REasoning on Three-View Line Drawings
SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding
[NeurIPS'24] SpatialEval: a benchmark to evaluate spatial reasoning abilities of MLLMs and LLMs
Qualitative Reasoning: Spatio-Temporal Reasoning using Relation Algebras and Constraint Networks. Documentation is under construction at ReadTheDocs. See link below.
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
Program synthesis for 3D spatial reasoning
[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)
A Tangram Puzzle Solver in Common Lisp that is capable of solving arbitrary geometric tiling problems. CLIM (Common Lisp Interface Manager) is used for its GUI.
[CVPR 2022] Self-supervised Spatial Reasoning on Multi-View Line Drawings
The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'
Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"
Grounding Language Models for Compositional and Spatial Reasoning
[NAACL 2022] Dataset and codes for the paper titled "Learning to Execute Actions or Ask Clarification Questions" in Findings of NAACL 2022
Code for "ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment"
DLMAPS = Description Logic Maps: Ontology-Based Spatial Queries to Digital City Maps
Official repo of the paper "Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models"
[ICLR 2025 Oral] Official Implementation for "Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities"
Measuring Massive Multimodal Understanding and Reasoning in Open Space
Add a description, image, and links to the spatial-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the spatial-reasoning topic, visit your repo's landing page and select "manage topics."