EvolvingLMMs-Lab / EASILinks
Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
☆31Updated last week
Alternatives and similar repositories for EASI
Users that are interested in EASI are comparing it to the libraries listed below
Sorting:
- [ICML 2025] VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models☆36Updated 5 months ago
- PhysGame Benchmark for Physical Commonsense Evaluation in Gameplay Videos☆46Updated 4 months ago
- [CVPR 2025]Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction☆144Updated 7 months ago
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆127Updated 2 months ago
- ☆45Updated last week
- [ACL2025 Oral & Award] Evaluate Image/Video Generation like Humans - Fast, Explainable, Flexible☆107Updated 3 months ago
- An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"☆140Updated last week
- ☆61Updated 2 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆190Updated 3 months ago
- ☆59Updated last week
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆178Updated last month
- ☆94Updated 4 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆167Updated last week
- Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆116Updated this week
- ☆62Updated 4 months ago
- Official implementation of "Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs".☆92Updated last week
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆62Updated 6 months ago
- Repo for paper "T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs"☆48Updated 2 months ago
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment☆61Updated 3 months ago
- ☆78Updated 4 months ago
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆118Updated 3 months ago
- Cambrian-S: Towards Spatial Supersensing in Video☆333Updated this week
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆170Updated 3 weeks ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆93Updated 8 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?