InstaDeep Ltd ORG

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

Foundation Models for Genomics & Transcriptomics

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

⚡ Flashbax: Accelerated Replay Buffers in JAX

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

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

Datasets with baselines for Offline MARL.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (SA), Tunisian Dialect Identification (TDI) and Reading Comprehension Question-Answering (RCQA)

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

:hibiscus: Population-Based Reinforcement Learning for Combinatorial Optimization

A tool for aggregating and plotting MARL experiment data.

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

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

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

🐈‍⬛ Contextual bandits library for continuous action trees with smoothing in JAX

🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX

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

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

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

Vectorization techniques for fast population-based training.

No description.

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

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

Official implementation of "Learning the language of protein structures"

BulkRNABert and MOJO

A LLM-friendly framework for translating dynamical equations to gymnasium-compatible RL environments.

Contrasting Sequence with Structure: Pre-training Graph Representations with PLMs

Official Implementation of Memento

Euclid-equivariant operations for JAX

A high-performance JAX library of equivariant mathematical operations for training AI models that simulate how atoms and molecules behave, with custom CUDA kernels that run faster than the earlier e3nn and e3x alternatives.

Experiments for performing empirical game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning.

Meta in-context learning for protein fitness prediction

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

Benchmarking and validation of Machine Learning Interatomic Potentials (MLIP)

A collection of matrix games in JAX

Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

Open-source reproductions of peptide-MHC presentation prediction models

LightMHC: A Light Model for pMHC Structure Prediction with Graph Neural Networks

Tutorial on Multi-Agent Reinforcement for Train Scheduling

Confidence control and FDR estimation for de novo peptide sequencing

Accelerated Quality-Diversity

⚡️ A framework that investigates the scaling limit of ResNets and compares it to Neural ODEs. Tested on synthetic and standardized datasets. 📈

No description.

A very fast distributed replay buffer for reinforcement learning

Official repository for Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning paper, accepted at the Reincarnating RL workshop at ICLR 2023.

Code for the paper (Neurips 25 Oral) "Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies"

No description.

No description.

Locust breeding ground prediction using pseudo-absence generation and machine learning.

Repository for the workshop at AMLD Africa 2021.

This repository contains the practical notebooks for the Indabax Tunisia 2019, held in Tunis on 13 April.

GitHub repository for the code release of the paper "Exploring the Conformational Landscape of Adenylate Kinase and Beyond: A Benchmark of Protein Folding Models"

Multi-Agent Transport Simulation

Materials for the TPU Workshop

IndabaX-SA-2021

InstaNovo-P: A De Novo Peptide Sequencing Model for Phosphoproteomics

Collection of smoke test with any operator, for AIchor platform

No description.

No description.

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Runner Container Hooks for GitHub Actions

MLflow Tracking Server OIDC Auth plugin

Repo to host a model context protocol for file uploading and downloading

Official GCP Provider for Crossplane by Upbound.

Community Helm Charts

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

No description.

Collection of smoke test with any operator, for AIchor platform

A machine learning compiler for GPUs, CPUs, and ML accelerators

Collection of smoke test with any operator, for AIchor platform

Collection of smoke test with any operator, for AIchor platform

Collection of smoke test with any operator, for AIchor platform

Collection of smoke test with any operator, for AIchor platform

Collection of smoke test with any operator, for AIchor platform

Collection of smoke test with any operator, for AIchor platform

No description.

No description.