The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
- 3d-reconstruction
- 3d-scenes
- monocular-depth
- monocular-depth-estimation
Repository Index
76,855 visible repositories in the index
25–39 of 39 · Most stars
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
- diffusion-models
- video-super-resolution
- video-restoration
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
- meta-rl
- multi-task
- benchmark-environments
- mujoco
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
- imitation-learning
- reinforcement-learning
- robotics
- simulation
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.
- generative-ai
- materials-design
- materials-science
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
- adaptive-learning
- machine-learning
- python
- live-plots
Hy-Nomas: Towards Free-form Interactive World Generation
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
:chart_with_upwards_trend: A live cryptocurrency historical trade data blotter. Download live historical trade data from any cryptoexchange, be it for machine learning, backtesting/visualizing trading strategies or for Quantopian/Zipline.
- cryptocurrency
- exchange
- trade
- data
Towards Reverse-Engineering Black-Box Neural Networks, ICLR'18
- neural-network
- blackbox
- iclr
- reverse-engineering
a parser for Forsyth-Edwards Notation (for encoding chess positions)