slime is an LLM post-training framework for RL Scaling.

Deepagents is an agent harness built on langchain and langgraph. Deep agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped …

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Train transformer language models with reinforcement learning.

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

A beautiful, simple, clean, and responsive Jekyll theme for academics

FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.

verl: Volcano Engine Reinforcement Learning for LLMs

Code and Data for Tau-Bench

Text-audio foundation model from Boson AI

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Fine-tuning Moshi/J-Moshi on your own spoken dialogue data

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Fully open reproduction of DeepSeek-R1