Highlights
- Pro
Stars
Open-source implementation of AlphaEvolve
Framework and toolkits for building and evaluating collaborative agents that can work together with humans.
verl: Volcano Engine Reinforcement Learning for LLMs
⚽️ Extract, prepare and publish Transfermarkt datasets.
(ICML'25 Outstanding) CollabLLM: From Passive Responders to Active Collaborators
🤗 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.
Solve puzzles. Improve your pytorch.
Which questions improve learning most? Utility Estimation of Questions with LLM-based Simulations
Kimi K2 is the large language model series developed by Moonshot AI team
Official Repo for MIME benchmark from ACL 2025 paper "Can Vision Language Models Understand Mimed Actions?"
A bibliography and survey of the papers surrounding o1
Mangrove is the backend module of Estuary, a framework for building multimodal real-time Socially Intelligent Agents (SIAs).
LOFT: A 1 Million+ Token Long-Context Benchmark
The official implementation of Self-Play Fine-Tuning (SPIN)
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/