Starred repositories
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Use LLMs to track and extract websites, RSS feeds, and social media
10BC0 Time-Series Work Summary in CS Top Conferences (NIPS, ICML, ICLR, KDD, AAAI, WWW, IJCAI, CIKM, ICDM, ICDE, etc.)
Kronos: A Foundation Model for the Language of Financial Markets
Predicting stock prices using a TensorFlow LSTM (long short-term memory) neural network for times series forecasting
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
An Open-source RL System from ByteDance Seed and Tsinghua AIR
An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions.…
Train transformer language models with reinforcement learning.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
On Memorization of Large Language Models in Logical Reasoning
Minimal reproduction of DeepSeek R1-Zero
No fortress, purely open ground. OpenManus is Coming.
DeepEP: an efficient expert-parallel communication library
Making large AI models cheaper, faster and more accessible
Fully open reproduction of DeepSeek-R1
An elegant PyTorch deep reinforcement learning library.
Submission for Optiver's 2023 ReadyTraderGo.