About Me



I am a fourth-year graduate student at EECS@MIT supervised by Prof. Gregory Wornell. I obtained my bacholor of science degree in computer engineering at UIUC, where I was fortunate to be advised by Prof. Yoram Bresler and Prof. Sanmi Koyejo.

I focus on enhancing trustworthiness in machine learning systems. This includes various aspects, including but not limited to uncertainty quantification, anomaly detection, and fairness. Furthermore, my recent research work has involved improving the interpretability, reliability, and efficiency of Large Language Models (LLMs) and developing multimodal LLMs.

Education

Massachusetts Institute of Technology(MIT)

2021 - 2023

M.S. in Electrical Engineering and Computer Science

2023 - 2026(expected)

Ph.D. in Electrical Engineering and Computer Science

GPA: 5.0/5.0

University of Illinois at Urbana-Champaign(UIUC)

2017 - 2021

B.S. in Computer Engineering

GPA: 4.0/4.0

Graduated with Highest Honors and Bronze Tablet

Work Experience

Research Internship at GenAI, Meta

Summer 2024

Research Internship at MIT-IBM Watson AI Lab

Summer 2023

Research Internship at MIT-IBM Watson AI Lab

Summer 2022

Publications

• Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation.
  Maohao Shen, Shun Zhang, Jilong Wu, Zhiping Xiu, Ehab AlBadawy, Yiting Lu, Mike Seltzer, Qing He
  Preprint (under review).

• Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
  Maohao Shen*, Jongha Jon Ryu*, Soumya Ghosh, Yuheng Bu, Prasanna Sattigeri, Subhro Das, Gregory Wornell.
  In Conference on Neural Information Processing Systems (NeurIPS), 2024.

• Thermometer: Towards Universal Calibration for Large Language Models.   [code]
  Maohao Shen, Subhro Das, Kristjan Greenewald, Prasanna Sattigeri, Gregory Wornell, Soumya Ghosh.
  In International Conference on Machine Learning (ICML), 2024.

• Group Fairness with Uncertainty in Sensitive Attributes.
  Abhin Shah, Maohao Shen, Jongha Jon Ryu, Subhro Das, Prasanna Sattigeri, Yuheng Bu, Gregory Wornell.
  In IEEE International Symposium on Information Theory (ISIT), 2024.

• On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation.   [code]
  Maohao Shen, Yuheng Bu, Gregory Wornell.
  In International Conference on Machine Learning (ICML), 2023.

• Reliable Gradient-free and Likelihood-free Prompt Tuning.   [code]
  Maohao Shen, Soumya Ghosh, Prasanna Sattigeri, Subhro Das, Yuheng Bu, Gregory Wornell.
  In Conference of the European Chapter of the Association for Computational Linguistics, Findings (EACL), 2023.

• Post-hoc Uncertainty Learning using a Dirichlet Meta-Model.   [code]
  Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell.
  In AAAI Conference on Artificial Intelligence (AAAI), 2023.

• Batch Active Learning from the Perspective of Sparse Approximation.
  Maohao Shen*, Bowen Jiang*, Jacky Y. Zhang*, Oluwasanmi Koyejo.
  In NeurIPS 2022 Workshop on Human in the Loop Learning.

• Labeling Cost Sensitive Active Learning for Brain Tumor Segmentation.
  Maohao Shen, Jacky Y. Zhang, Leihao Chen, Weiman Yan, Neel Jani, Brad Sutton, Oluwasanmi Koyejo.
  In IEEE International Symposium on Biomedical Imaging (ISBI’21), 2021.

(* indicates equal contribution)

Contact

maohao@mit.edu

maohaos2@illinois.edu

Misc.

• I like scuba diving and I am a PADI certified Advanced Open Water diver.

• I am a gourmet and I am good at cooking all kinds of dishes.

• I love Gelato.