Starred repositories
Staggeringly powerful macOS desktop automation with Lua
A rule-based tunnel for Android.
Repository of AAAI26 paper 'Flexible Concept Bottleneck Model'.
An open-source AI agent that brings the power of Gemini directly into your terminal.
A curated list of papers on reinforcement learning for video generation
267
Updated Nov 7, 2025
[Ultra Fast&Powerful Diffusion RL] Reinforcing Diffusion Models by Direct Group Preference Optimization
34
Updated Oct 11, 2025
Overleaf docker image with all packages available to tlmgr
[AAAI 2025] Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)
Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024]
LiYing is an automated photo processing program designed for automating the post-processing workflow of ID photos in general photo studios. | LiYing 是一套适用于自动化 完成一般照相馆后期证件照处理流程的照片自动处理的程序。
Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think
[MICCAI'2025] EndoDAV: Depth Any Video in Endoscopy with Spatiotemporal Accuracy
official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
自动抢票软件 CP31 哔哩哔哩 会员购 BW 漫展 脚本 抢票 |超级简单易用的哔哩哔哩会员购自动抢票工具，基于Rust开发的异步多线程高性能抢票软件。
The official implementation for ICML24 paper "Graph Out-of-Distribution Detection Goes Neighborhood Shaping"
The official implementation for ICLR25 paper "Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach Towards Quantum Error Mitigation"
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
A unified inference and post-training framework for accelerated video generation.
An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
The QEM-Bench code and datasets will be released shortly.
2
Updated May 30, 2025
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git