WorldEngine: Towards the Era of Post-Training for Physical AI

An Extensible Deep Learning Library

Strategic research thinking agents for Claude Code — idea evaluation, project triage, and structured brainstorming. Helps you decide which papers to write, not just how to write them.

AI agents running research on single-GPU nanochat training automatically

My learning notes for ML SYS.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

This repository contains the training code from paper "SpidR Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision". SpidR is a self-supervised speech representat…

The missing tiktoken training code

QLoRA: Efficient Finetuning of Quantized LLMs

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Post-training with Tinker

converter that creates three-dimensional models of the world from OpenStreetMap data

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

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

[ICML-2025] We introduce Lie group Relative position Encodings (LieRE) that goes beyond RoPE in supporting n-dimensional inputs.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

A high-throughput and memory-efficient inference and serving engine for LLMs

Simple RL training for reasoning

DeepSeek Coder: Let the Code Write Itself

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

A PyTorch native platform for training generative AI models

[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

Agile flight done right!

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

Modeling, training, eval, and inference code for OLMo

[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving