My new hobby 🎾 I moved to Atlanta in the summer of 2025, and since then my work-life balance got a lot better. With more free time, I started playing tennis again and taking lessons at the Piedmon...

Our paper “Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression” has been accepted to ICML 2026 and is available on arXiv. Swift-SVD studies low-rank compression...

Atmos Night This song, “Atmos Night”, was created through a joint effort between myself, GPT, and SUNO, written for personal reflection and as a small birthday project. The song reflects many la...

Sound Lab is an experimental space for exploring sound through the web and is now featured as a core section in the site’s sidebar. It hosts interactive tools for audio visualization, comparison, a...

NeurIPS 2025 Highlights: Audio Understanding and Generation Table of Contents Large Audio Language Models and Benchmark Spatial Audio  Audio Generation Audio Guided Generation 1. Larg...

Demo Music: Here is a MIDI-rendered version of “Prelude” from the Final Fantasy Games, which is further processed by FDN-Reverb. The Guitar tab:

This post was inspired by a conversation between me and a colleague about the difference between reverb pedals and room impulse responses. That discussion led me to revisit how reverb is represente...

📌 New Feature: DAILY ARXIV NEWS I just added a new dynamic page to my website — a Daily arXiv paper tracker that automatically fetches and filters newly released research papers based on my interes...

MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models I’m excited to share our new paper, MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language M...

I’ve earned my Songwriting certificate from Berklee Online via Coursera.