Xilin Jiang

me.jpg

Notre-Dame de la Garde, Marseille, France

I am a PhD candidate at Columbia University, in Electrical Engineering and Zuckerman Institute. I am a member of the Neural Acoustic Processing Lab supervised by Professor Nima Mesgarani. I build AI models and agents that listen and speak like humans. Recently, I am interested in how multimodal language models perceive and reason about the world, and how to better align them in behavior and in intention with human ears, eyes, and minds.

I am currently searching for 2026 research internships and collaborations.


Education

  • Columbia University, New York, NY

    Fall 2022 ~ Now 💻☕

    Ph.D. candidate after joint M.S. in Electrical Engineering

  • University of Illinois Urbana–Champaign, IL

    Fall 2018 ~ Fall 2021

    B.S. in Computer Engineering, with the Bronze Tablet 🏅🎓


Internship

  • Microsoft Research, Redmond, WA

    Summer 2025, Research Intern

    Mentors: Sebastian Braun & Hannes Gamper

    Project: Sci-Phi: A Large Language Model Spatial Audio Descriptor

  • Amazon, Palo Alto, CA

    Summer 2021 & 2022, SDE Intern


news

Jan 27, 2026 AVMeme Exam is public: A Multimodal Multilingual Multicultural Benchmark for LLMs’ Contextual and Cultural Knowledge and Thinking
Jan 17, 2026 My mentored paper SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models Accepted to ICASSP 2026🎉
Jan 13, 2026 My MSR intern paper Sci-Phi: A Large Language Model Spatial Audio Descriptor Accepted to IEEE Open Journal of Signal Processing 🎉
Nov 07, 2025 DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis Accepted to AAAI 2026 🎉
Oct 14, 2025 Bridging Ears&Eyes cross audio&visual LLM distill Won the Best Paper🥇 in WASPAA 2025