(* indicates equal contribution)

Intelligence: LLM Reasoning & Agent & RL

• SkillOS: Learning Skill Curation for Self-Evolving Agents.
   Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee
   Preprint.

• 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.

• FlowCompile: An Optimizing Compiler for Structured LLM Workflows.
   Junyan Li, Zhang-Wei Hong, Maohao Shen, Yang Zhang, Chuang Gan
   Preprint.

• Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering.
   Guangtao Zeng*, Maohao Shen*, Delin Chen, Zhenting Qi, Subhro Das, Dan Gutfreund, David Cox, Gregory Wornell, Wei Lu, Zhang-Wei Hong, Chuang Gan
   Preprint.

• Decocted Experience Improves Test-Time Inference in LLM Agents.
   Maohao Shen, Kaiwen Zha, Zexue He, Zhang-Wei Hong, Siru Ouyang, J. Jon Ryu, Prasanna Sattigeri, Suhas Diggavi, Gregory Wornell
   In Conference on Language Modeling (COLM), 2026

• RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning.   [code]
  Kaiwen Zha, Zhengqi Gao, Maohao Shen, Zhang-Wei Hong, Duane S. Boning, Dina Katabi
   In Conference on Neural Information Processing Systems (NeurIPS), 2025.

• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.   [code]
  Maohao Shen*, Guangtao Zeng*, Zhenting Qi*, Zhang-Wei Hong, Zhenfang Chen, Wei Lu, Gregory Wornell, Subhro Das, David Cox, Chuang Gan
  In International Conference on Machine Learning (ICML), 2025.

Interaction: Multimodal & Speech LLM

• UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation.
  Zeyuan Yang, Hao-Wei Chen, Xueyang Yu, Yuncong Yang, Haoyu Zhen, Ziqiao Ma, Maohao Shen, Chuang Gan
   Preprint.

• 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.

• Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens.   [code]
   Zeyuan Yang, Xueyang Yu, Delin Chen, Maohao Shen, Chuang Gan
  In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2026.

• 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.

Reliability: 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

• 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.

• 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.

maohao@mit.edu

maohaos2@illinois.edu