Stars
OpenS2S : Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
🔥🔥🔥 ICLR 2025 Oral. Automating Agentic Workflow Generation.
An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]
verl: Volcano Engine Reinforcement Learning for LLMs
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
[ICLR 2025] Benchmarking Agentic Workflow Generation
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
A virtual environment for developing and evaluating automated scientific discovery agents.
WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.
Build production-ready AI agents in both Python and Typescript.
Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined…
free and open OpenAI Deep Research
A curated list of papers on LLMs and agents for scientific research and development
🤗 smolagents: a barebones library for agents that think in code.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)
Word alignments generated by the Montreal Forced Aligner for the Librispeech dataset