facebookresearch / Multi-SpatialMLLMLinks
Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
☆167Updated 3 months ago
Alternatives and similar repositories for Multi-SpatialMLLM
Users that are interested in Multi-SpatialMLLM are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆126Updated 3 months ago
- A Large-scale Video Action Dataset☆376Updated 2 weeks ago
- [Nips 2025] EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆126Updated 6 months ago
- Official code for paper: N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models☆81Updated 3 weeks ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆426Updated 2 weeks ago
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆71Updated 3 months ago
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆334Updated 5 months ago
- Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"☆124Updated last month
- ☆122Updated 3 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆203Updated 9 months ago
- The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"☆206Updated this week
- A list of works on video generation towards world model☆334Updated this week
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆94Updated 7 months ago
- [CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning☆43Updated last year
- SPAgent, a spatial intelligence agent designed to operate in the physical and spatial world.☆85Updated last week
- The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)☆69Updated last week
- From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…☆75Updated last month
- Scaling Spatial Intelligence with Multimodal Foundation Models☆160Updated 3 weeks ago
- [ECCV 2024] M3DBench introduces a comprehensive 3D instruction-following dataset with support for interleaved multi-modal prompts.☆61Updated last year
- Unifying 2D and 3D Vision-Language Understanding☆121Updated 6 months ago
- Generative World Explorer☆165Updated 7 months ago
- ☆178Updated last week
- [NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.☆219Updated 3 months ago
- [ICLR 2026] OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models☆79Updated 2 weeks ago
- [ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields☆489Updated 3 months ago
- Self-reimplemented version of 4D-LRM.☆65Updated 8 months ago
- 4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)☆117Updated 10 months ago
- ☆162Updated last year
- Official implementation of DepthLM☆296Updated last week
- Code for "BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation", ICCV 2025.☆101Updated 3 months ago