DZ~/duo-zhou

TRUSTWORTHY AI / FROM OPTIMIZATION TO SELF-IMPROVING AGENTS

Duo Zhou

Ph.D. Student · Computer Science · UIUC

I am a Computer Science Ph.D. student at the University of Illinois Urbana-Champaign. I study how to make increasingly capable AI systems reliable - from the optimization and post-training methods that shape model behavior to the agents and multi-agent systems that act, coordinate, and improve over time. My work develops scalable algorithms, formal guarantees, and system-level mechanisms for reinforcement learning, neural network verification, and recursive self-improvement.

02 / UPDATE STREAM

News

recent.log

Show 9 earlier updates
02

Won VNN-COMP 2026 on CAV 2026.

03

InvSTG-PLM accepted to KDD 2026.

04

Lookahead Branching accepted to IJCAI 2026.

05

AdaFuse accepted to ACL 2026 Main.

06

DR-SAC accepted to ICLR 2026.

07

ShortageSim accepted to AAAI 2026 as an oral presentation.

08

Clip-and-Verify accepted to NeurIPS 2025.

09

Won VNN-COMP 2025 on CAV 2025.

10

BICCOS accepted to NeurIPS 2024.

03 / SELECTED OUTPUT

Publications

* equal contribution · † corresponding · Complete publication list on Google Scholar ↗

KDD '26

Invariant Structure Learning with Pre-trained Language Models for Spatio-temporal Graph

Ting Wang*, Duo Zhou*, Daqian Shi, Hao Tang, Hao Deng, Shengjie Zhao

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 5045-5056

ACL '26

AdaFuse: Adaptive Ensemble Decoding for Large Language Models

Chengming Cui*, Tianxin Wei*, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics · Main Conference, pp. 42644-42657

IJCAI '26

Lookahead Branching for Neural Network Verification

Liam Davis, Duo Zhou, Huan Zhang, Guy Katz, Clark W. Barrett, Haoze Wu

Proceedings of the 35th International Joint Conference on Artificial Intelligence

ICLR '26

DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty

Mingxuan Cui*, Duo Zhou*, Yuxuan Han, Grani A. Hanasusanto, Qiong Wang, Huan Zhang, Zhengyuan Zhou

The Fourteenth International Conference on Learning Representations Vol. 2026, pp. 92720-92750

PREPRINT

E-Globe: Scalable ε-Global Verification of Neural Networks via Tight Upper Bounds and Pattern-Aware Branching

Wenting Li, Saif R. Kazi, Russell Bent, Duo Zhou, Huan Zhang

arXiv preprint arXiv:2602.05068

SURVEY

Agentic Reasoning for Large Language Models

Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning, Ze Yang, Jiaru Zou, Zhichen Zeng, Ruizhong Qiu, Xiao Lin, Dongqi Fu, Zihao Li, Mengting Ai, Duo Zhou, Wenxuan Bao, Yunzhe Li, Gaotang Li, Cheng Qian, Yu Wang, Xiangru Tang, Yin Xiao, Liri Fang, Hui Liu, Xianfeng Tang, Yuji Zhang, Chi Wang, Jiaxuan You, Heng Ji, Hanghang Tong, Jingrui He

arXiv preprint arXiv:2601.12538

AAAI '26 Oral

ShortageSim: Simulating Drug Shortages under Information Asymmetry

Mingxuan Cui*, Yilan Jiang*, Duo Zhou*, Cheng Qian, Yuji Zhang, Qiong Wang

Proceedings of the AAAI Conference on Artificial Intelligence Vol. 40, No. 45, pp. 38321-38330

NeurIPS '25

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification

Duo Zhou*, Jorge Chavez*, Hesun Chen, Grani A. Hanasusanto, Huan Zhang

Advances in Neural Information Processing Systems 38, 174849-174895

NeurIPS '24

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes

Duo Zhou, Christopher Brix, Grani A. Hanasusanto, Huan Zhang

Advances in Neural Information Processing Systems 37, 29324-29353

ACC '24

Distributionally Robust Path Integral Control

Hyuk Park, Duo Zhou, Grani A. Hanasusanto, Takashi Tanaka

American Control Conference, pp. 1164-1171

IEEE TII

An Adaptive and Dynamical Neural Network for Machine Remaining Useful Life Prediction

Ruibing Jin*, Duo Zhou*, Min Wu, Xiaoli Li, Zhenghua Chen

IEEE Transactions on Industrial Informatics 20(2), 1093-1102

04A / MILESTONES

Honors

  • 01

    Winner of both the Regular and Extended tracks at VNN-COMP 2026.

  • 02

    Winner of both the Regular and Extended tracks at VNN-COMP 2025.

  • 03

    Winner of both the Regular and Extended tracks at VNN-COMP 2024.

  • 04

    First-Class Scholarship for the Graduating Class, 2021.

  • 05

    Meritorious Winner, Mathematical Contest in Modeling and Interdisciplinary Contest in Modeling, 2020.

  • 06

    Provincial First Prize, Contemporary Undergraduate Mathematical Contest in Modeling, 2019.

04B / COMMUNITY

Service

  • 01

    Reviewer: JMLR, NeurIPS, ICLR, ICML, AAAI, IJCAI, KDD, and ARR.