facebookresearch / Multi-SpatialMLLMLinks
Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
☆166Updated 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"☆122Updated 2 months ago
- [Nips 2025] EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆126Updated 5 months ago
- Official code for paper: N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models☆69Updated 3 weeks ago
- Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"☆121Updated 3 weeks ago
- ☆116Updated 2 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆420Updated last week
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆325Updated 4 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆198Updated 8 months ago
- Unifying 2D and 3D Vision-Language Understanding☆119Updated 5 months ago
- [CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning☆42Updated last year
- A list of works on video generation towards world model☆321Updated last week
- Official implementation of DepthLM☆284Updated last week
- The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"☆184Updated 2 weeks ago
- Scaling Spatial Intelligence with Multimodal Foundation Models☆151Updated this week
- Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”☆73Updated last month
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆192Updated last month
- From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perceptio…☆74Updated last week
- Trace Anything: Representing Any Video in 4D via Trajectory Fields☆456Updated 2 months ago
- Self-reimplemented version of 4D-LRM.☆65Updated 7 months ago
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆67Updated 2 months ago
- [ARXIV’25] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆86Updated 6 months ago
- Generative World Explorer☆165Updated 7 months ago
- Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling☆125Updated last month
- Implementation of paper "SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model"☆42Updated 2 weeks ago
- ☆162Updated last year
- The official implementation of The paper "Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation"☆94Updated 2 weeks ago
- 4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)☆116Updated 10 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆63Updated 5 months ago
- [ECCV 2024] M3DBench introduces a comprehensive 3D instruction-following dataset with support for interleaved multi-modal prompts.☆61Updated last year
- [NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding☆69Updated 3 months ago