Lists (9)
Stars
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Fully Open Framework for Democratized Multimodal Training
[arxiv 2025] RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
[NIPS 2025] FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
🔥🔥🔥 Latest Papers, Codes and Datasets on Video-LMM Post-Training
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention
Tongyi Deep Research, the Leading Open-source Deep Research Agent
slime is an LLM post-training framework for RL Scaling.
My learning notes/codes for ML SYS.
SGLang is a fast serving framework for large language models and vision language models.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
verl: Volcano Engine Reinforcement Learning for LLMs
Survey on LLM Agents (Published on CoLing 2025)
Mobile-Agent: The Powerful GUI Agent Family
GussianPretrain for Visual Pre-training in Autonomous Driving, showcasing significant improvements across various 3D perception tasks, including 3D object detection, HD-map construction, and Occupa…
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Integrate the DeepSeek API into popular softwares
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
Awesome Knowledge Distillation
This is a collective repository for all 3DGS related progresses in research and industry world
This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…
Solve Visual Understanding with Reinforced VLMs
[NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D