PzySeere / MetaSpatialLinks
MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, realistic, and adaptive scene generation for applications in the metaverse, AR/VR, and game development.
☆194Updated 7 months ago
Alternatives and similar repositories for MetaSpatial
Users that are interested in MetaSpatial are comparing it to the libraries listed below
Sorting:
- ☆102Updated last month
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆391Updated 5 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆98Updated 4 months ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆161Updated last month
- Cambrian-S: Towards Spatial Supersensing in Video☆407Updated 3 weeks ago
- A paper list for spatial reasoning☆471Updated this week
- ☆107Updated 4 months ago
- [NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding☆68Updated 2 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆62Updated 4 months ago
- ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models☆66Updated 6 months ago
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆182Updated 6 months ago
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆82Updated 4 months ago
- [arXiv 2025] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence☆60Updated last week
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆354Updated last month
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆57Updated last month
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆103Updated last month
- [NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"☆286Updated 11 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆197Updated 4 months ago
- From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…☆64Updated 2 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆186Updated last month
- [ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models …☆79Updated 6 months ago
- [Nips 2025] EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆122Updated 4 months ago
- A list of works on video generation towards world model☆225Updated last week
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆174Updated last week
- Code for "Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers" (NeurIPS 2024)☆199Updated last month
- Code&Data for Grounded 3D-LLM with Referent Tokens☆130Updated 11 months ago
- [NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration☆96Updated this week
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs☆55Updated 2 weeks ago
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆33Updated 5 months ago
- ☆30Updated last year