Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., pi0, pi0.5. Fully open-sourced.

Official implementation of Diffusion Policy Policy Optimization, arxiv 2024

Jax Codebase for Evolutionary Strategies at the Hyperscale

Official Repository of Absolute Zero Reasoner

Official implementation of "DiscoBench: An Open-Ended Benchmark For Algorithm Discovery"

Network Analysis in Python

Manipulation and analysis of geometric objects

[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

Code of paper "HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks"

Statically-linked, hermetic, relocatable Zsh

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official implementation for "How Should We Meta-Learn Reinforcement Learning Algorithms?"

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Implementation of Fully Sharded Data Parallelism in Jax

🚀 Efficient implementations of state-of-the-art linear attention models

Active reward modeling with last layer Fisher Information (ICML'25)

[ICML 2025 oral] Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

RSS 2023: This repository contains code for the paper Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors.

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians a…

A Survey of Reinforcement Learning for Large Reasoning Models

🤗 R1-AQA Model: mispeech/r1-aqa

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.