Xuan Shen
Email: shenxuan0516@gmail.com

I obtained my PhD degree in ECE Department of Northeastern University at Boston in August 2025, advised by Prof. Yanzhi Wang. Previously, I received my M.S. degree at Northeastern University in 2020 and my B.S. degree at Nanjing University of Science and Technology in 2018.
My research interests center on efficient deep learning, with a particular focus on optimizing large foundation models and diffusion models for text and visual generation. I emphasize scalability, latency reduction, and deployment efficiency across a wide range of hardware platforms, including GPUs, mobile devices, FPGAs, and ASICs.
Currently, I am a Postdoctoral Associate in the Department of Electrical and Computer Engineering at Cornell Tech of the Cornell University, where I work with Prof. Tianyi Chen.
News
Aug 14, 2025 | Ph.D. Defense Completed! |
---|---|
Jun 30, 2025 | Got one paper accepted in ICCAD 2025. |
Mar 06, 2025 | Our paper accepted in ICLR 2025 SCI-FM Workshop. |
Feb 26, 2025 | Got one paper accepted in CVPR 2025. |
Feb 02, 2025 | Release efficient reasoning work with paper and code. |
Jan 23, 2025 | Release the code of LazyDiT. |
Jan 22, 2025 | Got one paper accepted in ICLR 2025. |
Dec 09, 2024 | Got Adobe Reward: 2024 Key Innovations (Tech Transfer Small LLM on Acrobat). |
Dec 09, 2024 | Got three papers accepted in AAAI 2025. |
Nov 19, 2024 | Multimodal Opioid Benchmark released on HuggingFace: opioidarchive/oida-qa. |
Oct 30, 2024 | Our paper about PTQ of LLMs on Mobile and FPGA has been accepted to TCAD. |
Sep 25, 2024 | Got two papers accepted in NeurIPS 2024. |
Selected Publications
- ICLRSparse Learning for State Space Models on MobileInternational Conference on Learning Representations, 2025
- AAAINumerical Pruning for Efficient Autoregressive ModelsAssociation for the Advancement of Artificial Intelligence, 2025
- TCADHotaQ: Hardware Oriented Token Adaptive Quantization for Large Language ModelsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024