Portrait of Yize Li

Yize Li

Ph.D. Candidate@Northeastern University
li.yize@northeastern.edu Google Scholar LinkedIn Twitter

About

I am the final-year Ph.D. candidate in Computer Engineering at Northeastern University, advised by Prof. Xue (Shelley) Lin. I focus on generative multimodal machine learning in audio, vision, and language models. I also work closely with Prof. Yanzhi Wang (NEU), Prof. Sijia Liu (MSU), Prof. Andrew C. Singer (Dean from Stony Brook University) and Prof. Zhenglun Kong (Miami).

I am currently seeking full-time roles as a Machine Learning Engineer, Research Scientist, or Applied Scientist. Please feel free to reach out about any opportunities!

Research

My research interests lie in scalable, efficient, trustworthy, and generative multimodal machine learning, including:

  • Reasoning for Multimodal Large Language Models (MLLMs), including Vision-Language and Audio-Language Models.
  • Accelerations of Foundation Models such as Diffusion Models, Large Language Models, and Vision-Language Models.
  • Emerging Diffusion Large Language Models, Vision-Language Action Models, World Models, World Action Models, and AI Agent Systems.
  • Vision, Audio, and Speech Generative Foundation Models.
  • Energy-Efficient, Trustworthy and Robust AI Systems.

News

08/2026 Paper Our paper MRMAD is accepted to EMNLP Findings 2026.
07/2026 Project Our repo Awesome-Collection-Token-Reduction has received 500+⭐.
05/2026 Paper New preprint: a survey paper on Audio Super-Resolution.
04/2026 Paper Our paper Diff-StyGS is accepted to ICPR 2026.
12/2025 Presenting I gave a talk at Tufts University. The topic was “Towards Efficient, Trustworthy and Reasoning Generative Models.”
08/2025 Paper Our paper HDCompression is accepted to PRICAI 2025 as an Oral.
05/2025 Career Started internship at Bose Corporation as an Audio Research Intern.
05/2025 Paper New preprint: a position paper on Token Reduction in Generative Models.
04/2025 Paper Our paper FairSMoE is accepted to IJCAI 2025.
02/2025 Paper Our paper Data-Efficient Diffusion Model Training is accepted to ICASSP 2025.
01/2022 Paper Our paper is accepted to ICLR 2022.

Scroll down for more news

Selected Publications

Preprints

  1. P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution. Ningyuan Yang*, Yize Li*, Pu Zhao, Diego A. Cuji, Kanad Sarkar, Ryan M. Corey, Xue Lin, Andrew C. Singer. Under Review (2027).
  2. A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models. Ningyuan Yang*, Yize Li*, Diego A Cuji, Ryan M Corey, Pu Zhao, Xue Lin, Andrew C Singer. Under Review (2026). [arXiv]
  3. Token Reduction Should Go Beyond Efficiency in Generative Models--From Vision, Language to Multimodality. Zhenglun Kong*, Yize Li*, Fanhu Zeng, Lei Xin, Shvat Messica, Xue Lin, Pu Zhao, Manolis Kellis, Hao Tang, Marinka Zitnik. Under Review (2026). [arXiv]

Published

  1. MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models. Yize Li*, Ningyuan Yang*, Sile Yin, Sindhuja Thogarrati, Sung-En Chang, Andrew Singer, Xue Lin, Chuan-Che Huang, Shuo Zhang. [EMNLP 2026] Findings of the Association for Computational Linguistics: EMNLP 2026. [PDF] [Code]
  2. Diff-StyGS: 3D Gaussian Splatting Stylization via Tuning-Free Multi-View Sparse Diffusion. Yize Li, Lei Lu, Zhenglun Kong, Yanzhi Wang, Pu Zhao, Xue Lin. [ICPR 2026] International Conference on Pattern Recognition. [PDF]
  3. Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models. Yize Li, Yihua Zhang, Sijia Liu, Xue Lin. [ICASSP 2025] IEEE International Conference on Acoustics, Speech and Signal Processing. [PDF]
  4. HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates. Lei Lu*, Yize Li*, Yanzhi Wang, Wei Wang, Wei Jiang. [PRICAI 2025] Pacific Rim International Conference on Artificial Intelligence. [PDF]

Education

Ph.D. in Computer Engineering, Northeastern University May 2021 – Oct. 2026 (Expected)
Advisor: Prof. Xue (Shelley) Lin · Boston, MA
M.S. in Electrical and Computer Engineering, Northeastern University Sep. 2019 – May 2021
Advisor: Prof. Xue (Shelley) Lin · Boston, MA

Experience

Audio Research Intern, Bose Corporation May 2025 – Aug. 2026
Mentors: Dr. Chuan-Che Huang and Dr. Shuo Zhang · Framingham, MA

Service

Conference Reviewer: AAAI, BMVC, CVPR, ECCV, ICASSP, ICCV, ICLR, ICML, IJCAI, IJCNN, NeurIPS, WACV
Journal & Workshop Reviewer: IEEE TCAD, IEEE TSP, DCASE 2026, IEEE MLSP 2026