Embedded Files
Contact information:
Cell: (218)-590-1833
Email: wangfuli610 at gmail dot com
Welcome to my website! My name is Fuli Wang (王馥黎 in Chinese). I am an LLM research engineer at Apple, working on Apple Foundation Model Optimization including quantization-aware training and multimodal use-case adaptation.
Before this, I did my Ph.D. at University of Delaware, where I was fortunate to with my advisors Prof. Gonzalo R. Arce and Prof. Wei Qian on graph signal processing and machine learning.
I am interested in building effective and efficient methods to enhance foundation models, exploring the science behind them and making them useful for production delivery.
NEWS:
[Feb 2025] Our paper "Towards Retrieval-Augmented Large Language Model-Based Conversational Recommender System" is accepted by PAKDD.
[Sep 2024 ] Our paper "Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets" is submitted to TPAMI.
[July 2024 ] I started working as an AIML resident at Apple.
[ July 2024 ] I successfully defended my dissertation and became Dr. Wang! 😃
[Nov 2023 ] Our paper "T-HyperGNNs: Hypergraph Neural Networks Via Tensor Representations " is accepted by IEEE Transaction on Neural Networks and Learning Systems, and the early access is available here.
[Nov 2023 ] Our paper "Learning Hypergraphs Tensor Representations from Data via t-HGSP" is accepted by IEEE Transactions on Signal and Information Processing over Networks, and is available here.
[June 2023 ] Our paper "A Unified View Between Tensor Hypergraph Neural Networks and Signal Denoising" has been accepted by EUSIPCO 2023 and is available here.
[June 2023 ] I am presenting our work on tensor hypergraph neural networks at the graph signal processing workshop 2023 in Oxford, UK. The slides are available here.
[Nov 2022 ] Pass Ph.D. dissertation proposal defense!
[Aug 2022 ] Start online master of computer science at Georgia Institute of Technology.
[July 2021 ] Pass Ph.D. qualifying exams!
[Aug 2020 ] Start working with Prof. Arce and Prof. Qian on hypergraph learning.
Page updated
Google Sites
Report abuse