Owner

instadeepai

27 indexed repositories · View on GitHub

• Mava

  🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

  Python · 935 stars

• nucleotide-transformer

  Foundation Models for Genomics & Transcriptomics

  Jupyter Notebook · 920 stars

• jumanji

  🕹️ A diverse suite of scalable reinforcement learning environments in JAX

  Python · 862 stars

• flashbax

  ⚡ Flashbax: Accelerated Replay Buffers in JAX

  Python · 283 stars

• og-marl

  Datasets with baselines for Offline MARL.

  Python · 232 stars

• mlip

  Library for efficient training and application of Machine Learning Interatomic Potentials (MLIP)

  Python · 134 stars

• InstaNovo

  De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments

  Python · 131 stars

• InstaGeo-E2E-Geospatial-ML

  A python package for end-to-end geospatial machine learning using multispectral earth observation data such as NASA HLS and ESA Sentinel-2.

  Python · 88 stars

• marl-eval

  A tool for aggregating and plotting MARL experiment data.

  Python · 87 stars

• manyfold

  🧬 ManyFold: An efficient and flexible library for training and validating protein folding models

  Python · 80 stars

• AlphaNPI

  Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.

  Python · 79 stars

• DebateLLM

  Benchmarking Multi-Agent Debate between Language Models for Truthfulness in Q&A.

  Jupyter Notebook · 62 stars

• FrameDiPT

  FrameDiPT: an SE(3) diffusion model for protein structure inpainting

  Jupyter Notebook · 61 stars

• awesome-marl

  A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers

  58 stars

• fastpbrl

  Vectorization techniques for fast population-based training.

  Python · 58 stars

• protein-sequence-bfn

  Supporting code for our paper "Protein Sequence Modelling with Bayesian Flow Networks"

  Python · 53 stars

• compass

  :compass: COMPASS: Combinatorial Optimization with Policy Adaptation using Latent Space Search

  Python · 47 stars

• protein-structure-tokenizer

  Official implementation of "Learning the language of protein structures"

  Python · 42 stars

• multiomics-open-research

  Open-source foundation models for multi-omics representation learning

  Python · 42 stars

• AbBFN2

  AbBFN2: A flexible antibody foundation model based on Bayesian Flow Networks

  Python · 39 stars

• 7 more repositories live on View on GitHub