Benchmark and training code for MindCube: spatial mental modeling in vision-language models from limited views.
☆168Aug 23, 2026Updated last week
Alternatives and similar repositories for MindCube
Users that are interested in MindCube are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence☆108Apr 28, 2026Updated 4 months ago
- THEORY OF SPACE: a benchmark for evaluating whether foundation models can actively explore under partial observability efficiently to bui…☆86Feb 27, 2026Updated 6 months ago
- From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…☆95Jan 5, 2026Updated 7 months ago
- [CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models☆298May 14, 2026Updated 3 months ago
- A paper list for spatial reasoning☆779Aug 23, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [CVPR 2026] Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views☆253May 7, 2026Updated 3 months ago
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆256Nov 28, 2025Updated 9 months ago
- World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).☆494Updated this week
- [NeurIPS 2025 Spotlight] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆485Feb 5, 2026Updated 6 months ago
- Holistic Evaluation of Multimodal LLMs on Spatial Intelligence☆123Jul 1, 2026Updated 2 months ago
- [CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆443Jul 15, 2026Updated last month
- [ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models☆99Jun 9, 2026Updated 2 months ago
- ENACT is a benchmark that evaluates embodied cognition through world modeling from egocentric interaction. It is designed to be simple an…☆53Nov 27, 2025Updated 9 months ago
- [ICLR2026] Spatial Reasoning with Vision-Language Models☆64Jan 26, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official repo and evaluation implementation of VSI-Bench☆738Aug 5, 2025Updated last year