A Lightweight LLM Post-Training Library

Agentic AutoResearch scaffold for modular Diffusers experiments on JarvisLabs

https://deep-diver.github.io/tunix-accel/

dLLM training implementation on pure jax/flax (w/o pytorch) for Google TPUs(v4/v5e/v6e). #TPUSprint #TRC

Diffusion model research harness built on Keras 3 + JAX — unconditional DDPM, classifier-free guidance, and more

[ACL'26] Official Code for "ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning"

[arXiv'26] Official Code for "WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning"

Run ML workloads seamlessly on cloud TPUs and GPUs with a single Python decorator. No infrastructure management required.

🖥 Neural Computers' Data Engine

A library for Multilingual Unsupervised or Supervised word Embeddings

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

Algorithm powering the For You feed on X

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.

Generate unique fashion moodboards to find your next design inspiration.

Agentic RL Training at Scale

Dream 7B, a large diffusion language model

Train transformer language models with reinforcement learning.

Easy and Efficient dLLM Fine-Tuning

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

AlexNet model from ILSVRC 2012

The best ChatGPT that $100 can buy.

A Lightweight LLM Post-Training Library