Open-source AI skills and plugins for EB-1 and EB-2 NIW immigration petitions — from case evaluation to RFE response. Built for Claude.

verl: Volcano Engine Reinforcement Learning for LLMs

Config files for my GitHub profile.

CudaForge with integrated Stark support

Official Repo of CudaForge

[ACL2026 Findings] Official implementation for Human-Agent Collaborative Paper-to-Page Crafting

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

s1: Simple test-time scaling

GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Code listing for the paper 'BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks'. Work in progress.

XJTU Luo Lab undergraduate division website

Official repository of "KGQUIZ: Evaluating the Generalization of Encoded Knowledge in Large Language Models". TheWebConf 2024.

Config files for my GitHub profile.

Personal website of Yuyang Bai

Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would train Wav2Lip on CMLR. Wish it would do better in Chinese.

My Blog

Some useful tutorial for rookies (程序猿的救星)

✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】

Tensors and Dynamic neural networks in Python with strong GPU acceleration