Tongyi Deep Research, the Leading Open-source Deep Research Agent

Native Swift and CoreML SDK for local speaker diarization, VAD, and speech-to-text for real-time workloads. Works on iOS and macOS.

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

Frontier Open-Source Text-to-Speech

PyTorch → CoreML conversion pipeline for Kokoro TTS. Unlocks fast on-device text-to-speech on Apple Neural Engine.

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…

Solana Swiss Army Knife

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Personal contributions to Streamlit Components

Robust Speech Recognition via Large-Scale Weak Supervision

Bringing Old Photo Back to Life (CVPR 2020 oral)

The implementation of focal loss proposed on "Focal Loss for Dense Object Detection" by KM He and support for multi-label dataset.

Bare bones Python implementations of some of the foundational Machine Learning models and algorithms.

Notes from interesting things that I've read.

A complete daily plan for studying to become a Google software engineer.

Interview questions

Simple yet powerful and really extendable application for managing a blog within your Django Web site.

C++ Primer 5ed answers