颈椎病腰突康复指南，为程序员群体提供简单可靠的康复指南。

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

A fork to add multimodal model training to open-r1

Simple RL training for reasoning

The official implementation of Natural Language Fine-Tuning

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

PyTorch implementation of DreamerV3, Mastering Diverse Domains through World Models.

a distributed deep learning platform

Simple maze environments using mujoco-py

Implementation of Dreamer v3 in pytorch.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

A curated list of awesome model based RL resources (continually updated)

Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.