EvolvingLMMs-Lab / EASILinks
Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
☆77Updated 2 weeks ago
Alternatives and similar repositories for EASI
Users that are interested in EASI are comparing it to the libraries listed below
Sorting:
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆64Updated last week
- Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"☆109Updated last month
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆117Updated last week
- Cambrian-S: Towards Spatial Supersensing in Video☆488Updated last month
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆137Updated 5 months ago
- ☆68Updated 3 months ago
- ☆122Updated 3 months ago
- InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models☆77Updated this week
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆207Updated 3 months ago
- Official Repository for paper "HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding"☆51Updated 2 weeks ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆103Updated 7 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆86Updated 6 months ago
- ☆117Updated 6 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆240Updated 6 months ago
- ☆97Updated 7 months ago
- ☆63Updated last week
- ☆41Updated 7 months ago
- The first HEVC style Vision Transformer with advanced multimodal capabilities☆83Updated this week
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆203Updated 9 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆64Updated 6 months ago
- [NeurIPS 2025] Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆90Updated 6 months ago
- [NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration☆113Updated 2 months ago
- MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence☆54Updated last month
- ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO☆78Updated 2 months ago
- ☆63Updated last month
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆237Updated last week
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆273Updated 3 months ago
- Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆129Updated last month
- PyTorch implementation of NEPA☆308Updated 2 weeks ago
- A collection of awesome think with videos papers.☆86Updated 2 months ago