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. Sanmi Koyejo and Prof. Yoram Bresler.
My primary research goal is to contribute towards achieving Artificial General Intelligence (AGI). AGI presents three critical challenges: matching or surpassing human-level intelligence, ensuring safety and reliability, and effectively acquiring and processing information across multiple modalities. To address these challenges, my research interests focus on:
- Enhancing the reasoning capabilities of LLMs and agents.
- Improving the reliability, safety, and trustworthiness of machine learning systems.
- Developing multimodal LLMs: vision language model, speech language model.
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 Meta Superintelligence Lab (MSL)
Summer 2025
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
(* indicates equal contribution)
LLM Reasoning & Agent & RL
• PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory.
Bowen Jiang, Yuan Yuan, Maohao Shen, Zhuoqun Hao, Zhangchen Xu, Zichen Chen, Ziyi Liu, Anvesh R. Vijjini, Jiashu He, Hanchao Yu, Radha Poovendran, Gregory Wornell, Lyle Ungar, Dan Roth, Sihao Chen, Camillo J. Taylor
Preprint.
Multimodal: VLM & Speech LLM
• GSRM: Generative Speech Reward Model for Speech RLHF.
Maohao Shen*, Tejas Jayashankar*, Osama Hanna*, Naoyuki Kanda*, Yancheng Wang, Kateřina Žmolíková, Ruiming Xie, Niko Moritz, Anfeng Xu, Yashesh Gaur, Gregory Wornell, Qing He, Jilong Wu
Preprint.
• VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation.
Yancheng Wang, Osama Hanna, Ruiming Xie, Xianfeng Rui, Maohao Shen, Xuedong Zhang, Christian Fuegen, Jilong Wu, Debjyoti Paul, Arthur Guo, Zhihong Lei, Ozlem Kalinli, Qing He, Yingzhen Yang
In International Conference on Learning Representations (ICLR), 2026.
• VCA: Video Curious Agent for Long Video Understanding.
Zeyuan Yang, Delin Chen, Xueyang Yu, Maohao Shen, Chuang Gan
In International Conference on Computer Vision (ICCV), 2025.
• 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
In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025.
Trustworthy AI & AI Safety
• Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? [code]
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.
• 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.
General Machine Learning & Application
•
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.
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.