Hi, I’m a Machine Learning Engineer at Google, where I work on YouTube’s recommender systems. My work focuses on LLM-based generative recommendation, large-scale retrieval models, multimodal content understanding, user cold-start, etc.
Before Google, I obtained a PhD in Neuroscience from the University of Utah, where I studied human brain development using neurophysiology and computational genomic technologies, advised by Dr. Alex Shcheglovitov.
In addition, I received a MS in Computer Science from Columbia University, and a BS in Biological Sciences from Peking University.
Selected Publications
1. Machine Learning
- Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on AcceleratorsarXiv preprint, 2026
- PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative RecommendationsWWW, 2025
- LLM-Powered Nuanced Video Attribute Annotation for Enhanced RecommendationsRecSys, 2025
- Amortized Probabilistic Detection of Communities in GraphsICML SPIGM Workshop, 2024
- LLMs for user interest exploration in large-scale recommendation systemsRecSys, 2024
- Learning from negative user feedback and measuring responsiveness for sequential recommendersRecSys, 2023
- Neural Clustering ProcessesICML, 2020
- Spike Sorting using the Neural Clustering ProcessNeurIPS NeuroAI Workshop, 2019
2. Neuroscience
- Modeling human telencephalic development and autism-associated SHANK3 deficiency using organoids generated from single neural rosettesNature communications, 2022
- Defective AMPA-mediated synaptic transmission and morphology in human neurons with hemizygous SHANK3 deletion engrafted in mouse prefrontal cortexMolecular psychiatry, 2021
- Heterophilic type II cadherins are required for high-magnitude synaptic potentiation in the hippocampusNeuron, 2017
Full publication list on Google Scholar.
