Lists (6)
Starred repositories
Source code for the paper "Guarantees for Greedy Maximization of Non-submodular Functions with Applications" in ICML 2017
[ICML 2025] Hierarchical Graph Tokenization for Molecule-Language Alignment
An open, large-scale, interactive textbook.
Collecting research materials on neural samplers with diffusion/flow models
[NeurIPS25 Spotlight] EMPO, A Fully Unsupervised RLVR Method
An electronic structure package based on either plane wave basis or numerical atomic orbitals.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Genome modeling and design across all domains of life
Minimal reproduction of DeepSeek R1-Zero
A trainable PyTorch reproduction of AlphaFold 3.
AlphaFold 3 inference pipeline.
Training Sparse Autoencoders on Language Models
Thermodynamically Explainable Representations of AI and other black-box Paradigms
Implementation of Alphafold 3 from Google Deepmind in Pytorch
Open source implementation of AlphaFold3
List of papers studying machine learning through the lens of category theory
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
[ICML 2024] How Interpretable Are Interpretable Graph Neural Networks?
Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)
The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"
A high-throughput and memory-efficient inference and serving engine for LLMs
Tools for merging pretrained large language models.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A collection of AWESOME things about mixture-of-experts