The simplest, fastest repository for training/finetuning medium-sized GPTs.

Exploring Expert Failures Improves LLM Agent Tuning

SGLang is a fast serving framework for large language models and vision language models.

UCLA Thesis LaTeX style

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

[NAACL 2025] The official implementation of paper "Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents"

[ICML'2023 Oral] "AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners"

[CoRL'23] Parting with Misconceptions about Learning-based Vehicle Motion Planning

Hydra is a framework for elegantly configuring complex applications

The devkit of the nuPlan dataset.

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Sample efficiency and generalisation in reinforcement learning using procedural generation.

research

PyTorch code to train and evaluate Procgen tasks

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework

Attack AlphaZero Go agents (NeurIPS 2022)

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).

[NeurIPS 2020 Spotlight] State-adversarial PPO for robust deep reinforcement learning

RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.

PECOS - Prediction for Enormous and Correlated Spaces