-
Research Fellow@CityU
- Hangzhou, China
- https://scholar.google.com.hk/citations?user=gjMTPgkAAAAJ
- https://hongwei.me
Stars
- All languages
- ASP
- ActionScript
- Arduino
- Assembly
- Ballerina
- Blade
- C
- C#
- C++
- CSS
- CoffeeScript
- Cuda
- Cython
- Dockerfile
- Go
- HTML
- Hack
- Java
- JavaScript
- Jupyter Notebook
- Less
- Lua
- MATLAB
- Makefile
- Mermaid
- Objective-C
- OpenEdge ABL
- PHP
- Perl
- Perl 6
- Processing
- Pug
- Python
- QML
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Svelte
- Swift
- TSQL
- TeX
- TypeScript
- VHDL
- Verilog
- Vue
- WebAssembly
🎯 告别信息过载,AI 助你看懂新闻资讯热点,简单的舆情监控分析 - 多平台热点聚合+基于 MCP 的AI分析工具。监控35个平台(抖音、知乎、B站、华尔街见闻、财联社等),智能筛选+自动推送+AI对话分析(用自然语言深度挖掘新闻:趋势追踪、情感分析、相似检索等13种工具)。支持企业微信/个人微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 推送,1分钟手机通知,无需…
[ICLR 2025] The First Multimodal Seach Engine Pipeline and Benchmark for LMMs
Official implementation of the paper “Endowing Vision-Language Models with System 2 Thinking for Fine-Grained Visual Recognition,” AAAI 2026.
Continuous Thought Machines, because thought takes time and reasoning is a process.
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Train your Agent model via our easy and efficient framework
🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access
A research prototype of a human-centered web agent
Fara-7B: An Efficient Agentic Model for Computer Use
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
The only production-ready open-source AI guardrails platform for enterprise AI applications with user-defined scanners and custom model training support.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。
智能闲鱼客服机器人系统:专为闲鱼平台打造的AI值守解决方案,实现闲鱼平台7×24小时自动化值守,支持多专家协同决策、智能议价和上下文感知对话。
Official Python SDK for the Agent2Agent (A2A) Protocol
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, …
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Formula recognition based on LaTeX-OCR and ONNXRuntime.
Bridging LLM and Recommender System.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.