AI Train2023
Trains LLMs with RLHF at scale by splitting actor, critic, reward, and reference models across separate GPU groups via Ray, with vLLM-accelerated generation and DeepSpeed ZeRO-3. Supports PPO, GRPO, REINFORCE++, DPO, plus async and agentic multi-turn RL.
Embodied AI2024
A PyTorch-native, hardware-agnostic stack for robot learning: data collection, training, and deployment across 11+ robots, from SO100 to Unitree G1. Includes imitation, RL, and vision-language-action policies (ACT, Diffusion, Pi0, SmolVLA).
Reaches 51.7% on the competition-level MATH benchmark with a 7B model and no tools or voting, rivaling Gemini-Ultra and GPT-4. Built on a 120B-token math corpus mined from Common Crawl, and introduces GRPO, a memory-efficient PPO variant for reasoning.
Hands-on coding tutorial series for large language models with slides and runnable notebooks covering fine-tuning, prompting, RLHF, safety, steganography, watermarking, multimodal models, GUI agents, and deployment. Community-maintained, free course materials for students and researchers.
Embodied AI2024
GPU‑accelerated framework for training physically simulated humanoid characters and robots using reinforcement learning and motion imitation. Provides a modular multi‑backend simulator stack, large‑scale multi‑GPU training recipes, built‑in motion retargeting and an ONNX deployment pathway to real robots.
AI Train2024
Open-source HybridFlow implementation for RL post-training of LLMs. Decouples control flow from compute so PPO, GRPO, GSPO and DAPO share one dataflow; pairs FSDP/Megatron with vLLM/SGLang rollout and reports 1.5-20x throughput over prior RLHF stacks.
A GitHub repository of learning notes and code dedicated to ML + SYS (machine learning systems). It collects tutorials, code walkthroughs and engineering notes on RLHF, distributed training (FSDP, Megatron), inference and scheduling (SGLang, vllm), quantization, CUDA/GPU optimization, system design, and practical engineering.
AI Train2025
Bundles a dataset, an interaction harness, and rubric-based reward functions into one RL environment for training and evaluating LLMs — also usable as an eval, synthetic-data pipeline, or agent harness for any OpenAI-compatible endpoint.
AI Infra2025
Spins up sandboxed VMs and containers (macOS, Linux, Windows, Android) that an AI agent can fully control through one unified SDK, cloud or local, plus a benchmark suite and background drivers that automate native apps without grabbing the cursor.
AI Train2025
An asynchronous, high-throughput framework for large-scale reinforcement learning and agentic training that scales to 1T+ MoE models and 1000+ GPUs, with native verifiers integration, end-to-end SFT/RL/evals, and Slurm/Kubernetes deployment; requires NVIDIA GPUs.
AI Train2025
inclusionAI (AReaL Team), Institute for Interdisciplinary Information Sciences, Tsinghua University +1Ant Group, Institute for Interdisciplinary Information Sciences, Tsinghua University
Trains LLM reasoning and agentic models with fully asynchronous reinforcement learning, decoupling rollout generation from policy updates for a 2.77x speedup over synchronous RL. Covers GRPO, PPO and DAPO across Megatron, FSDP, vLLM and SGLang backends.
AI Agent2025
Build and run configurable multi-agent LLM workflows and personal AI agents locally or with cloud LLMs; supports simple TOML-based LLM configuration, optional browser automation, a demo on Hugging Face, and companion RL tuning (OpenManus-RL) for agent training.