zhengxuJosh / Awesome-Multimodal-Spatial-ReasoningLinks
This repository collects and organises state‑of‑the‑art papers on spatial reasoning for Multimodal Vision–Language Models (MVLMs).
☆249Updated last week
Alternatives and similar repositories for Awesome-Multimodal-Spatial-Reasoning
Users that are interested in Awesome-Multimodal-Spatial-Reasoning are comparing it to the libraries listed below
Sorting:
- [ArXiv 2025] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models☆68Updated last week
- ☆449Updated this week
- Official implementation of "Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs".☆94Updated last month
- This is the official Python version of Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play.☆104Updated 2 months ago
- A Scientific Multimodal Foundation Model☆620Updated 2 months ago
- [ACL2025 Oral & Award] Evaluate Image/Video Generation like Humans - Fast, Explainable, Flexible☆113Updated 4 months ago
- This is the offical repository of InfiniteVL☆54Updated last week
- Cambrian-S: Towards Spatial Supersensing in Video☆429Updated last week
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆123Updated 5 months ago
- 📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.☆370Updated this week
- PyTorch implementation of NEPA☆70Updated this week
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆256Updated last month
- Fully Open Framework for Democratized Multimodal Training☆662Updated last week
- Visual Planning: Let's Think Only with Images☆287Updated 7 months ago
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆244Updated last month
- OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.☆607Updated last month
- A Definition of Scientific General Intelligence☆57Updated this week
- The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"☆172Updated this week
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆335Updated 6 months ago
- ☆64Updated 5 months ago
- Holistic Evaluation of Multimodal LLMs on Spatial Intelligence☆50Updated this week
- StreamingVLM: Real-Time Understanding for Infinite Video Streams☆771Updated 2 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆411Updated 2 weeks ago
- Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"☆94Updated last month
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆710Updated last week
- Codebase for paper ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools☆19Updated last month
- [MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."☆141Updated 5 months ago
- ☆191Updated 6 months ago
- ☆181Updated 5 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆215Updated 4 months ago