A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.

Elevate your AI research writing, no more tedious polishing ✨

A collection of paper/projects that trains flow matching model/policies via RL.

iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

🎁 A collection of utilities for LeRobot.

Official implementation of the paper: Task Reconstruction and Extrapolation for $\pi_0$ using Text Latent (https://arxiv.org/pdf/2505.03500)

iNode_Client_Sequoia inode 客户端Sequoia支持第三方版本,教程：https://player.bilibili.com/player.html?aid=113583849478266

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

Benchmarking Knowledge Transfer in Lifelong Robot Learning