Weitong Zhang

Weitong Zhang

Assistant Professor, School of Data and Information Sciences (SDIS)

Publications

You can also find my recent publications on my Google Scholar profile.

* means Equal Contribution.

  1. Yu, T., Yang, Y., Wang, Z., Zhao, K., Jenkins, P., Zhang, X., Bansal, C., Yao, H., & \textbfWeitong Zhang. (2026). Provable and Practical In-Context Policy Optimization for Self-Improvement. International Conference on Learning Representations (ICLR 2026).
  2. Li, S., Zhou, D., & Zhang, W. (2026). Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning. International Conference on Learning Representations.
  3. Li, S., Zhang, X., Bansal, C., & \textbfWeitong Zhang. (2026). Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning. ArXiv Preprint ArXiv:2602.01357.
  4. Qu, Y., Li, S., & Zhang, W. (2026). Imitation from Observations with Trajectory-Level Generative Embeddings. ArXiv Preprint ArXiv:2601.00452.
  5. Liang, Y., Liu, S., & \textbfWeitong Zhang. (2026). Moment Matching Q-Learning. International Conference on Machine Learning (ICML 2026).
  6. Yang, Y., & \textbfWeitong Zhang. (2026). Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning. International Conference on Machine Learning (ICML 2026).
  7. Yang, Y., Wang, X., & \textbfWeitong Zhang. (2026). OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning. ArXiv Preprint ArXiv:2605.12400.
  8. Yu, T., Zhao, K., Chen, C.-C., Hughes, A., Killian, T. W., Ma, F., \textbfWeitong Zhang, & Jenkins, P. (2026). LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation. ArXiv Preprint ArXiv:2605.30651.
  9. Liang, S., & \textbfWeitong Zhang. (2026). Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation. ArXiv Preprint ArXiv:2604.13966.
  10. \textbfWeitong Zhang. (2026). Reinforcement Learning Without Explicit Rewards: Theory and Practice. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39847–39847. https://doi.org/10.1609/aaai.v40i47.41364
  11. Huang, A., Stanley, J. S., Lai, Y.-A., Sheng, H., Zou, H., Chen, H. M., Costentin, C., Qi, L., Yang, J. Y., \textbfWeitong Zhang, & Liu, C. (2026). Latent mechanism mapping in self-driving molecular electrocatalysis. Submitted Preprint.
  12. Lai, Y.-A., Xiong, M., Sun, J., Huang, A., Fleet, M. V., Sheng, H., Kim, J., Kuo, F., Lai, T. Y., Lin, X.-R., Chen, Y.-A., \textbfWeitong Zhang, Chen, H. M., & Liu, C. (2026). Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis. Submitted Preprint.
  13. Sun, J., \textbfWeitong Zhang, Zhao, Q., Gu, Q., & Liu, C. (2026). EIS-GPT: Transformer-based generation of equivalent circuit for electrochemical impedance spectroscopy. ChemRxiv Preprint. https://doi.org/10.26434/chemrxiv.15002939/v1
  14. Wang, Y., Li, S., Niu, H., Huang, Z., Zhang, W., & Su, H. (2025). A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models. ArXiv Preprint ArXiv:2510.02538.
  15. Zhou, Y., Wang, Z., Wang, T., Xing, S., Xia, P., Li, B., Zheng, K., Zhang, Z., Chen, Z., Zheng, W., Zhang, X., Bansal, C., Zhang, W., Wei, Y., Bansal, M., & Yao, H. (2025). AnyPrefer: An Automatic Framework for Preference Data Synthesis. International Conference on Learning Representations.
  16. Lan, Y., Cao, Y., Zhang, W., Lin, L., & Chen, J. (2025). Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time. The 2025 Conference on Empirical Methods in Natural Language Processing \Textbf(Oral).
  17. Wang, Z., He, W., Liang, Z., Zhang, X., Bansal, C., Wei, Y., Zhang, W., & Yao, H. (2025). CREAM: Consistency Regularized Self-Rewarding Language Models. International Conference on Learning Representations.
  18. Sun, J., Zhang, W., Chen, Y., Hoar, B. B., Sheng, H., Yang, J. Y., Gu, Q., & Liu, C. (2025). Inquiry into the Appropriate Data Preprocessing of Electrochemical Impedance Spectroscopy for Machine Learning. The Journal of Physical Chemistry C.
  19. Zhang, S., Zhang, W., & Gu, Q. (2025). Energy-Weighted Flow Matching for Offline Reinforcement Learning. International Conference on Learning Representations.
  20. Zhao, L., Deng, Y., Zhang, W., & Gu, Q. (2025). Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance. Forty-Second International Conference on Machine Learning \Textbf(Spotlight). https://openreview.net/forum?id=w0xYx9CJhY
  21. Zheng, W., Chen, Y., Zhang, W., Kundu, S., Li, Y., Liu, Z., Xing, E. P., Wang, H., & Yao, H. (2024). CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing. Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning.
  22. Braverman, A., Zhang, W., & Gu, Q. (2024). Mitigating Hallucination in Large Language Models with Explanatory Prompting. Statistical Foundations of LLMs and Foundation Models (NeurIPS 2024 Workshop). https://openreview.net/forum?id=wWDRQs1pX8
  23. Zhang, J., Zhang, W., Zhou, D., & Gu, Q. (2024). Uncertainty-Aware Reward-Free Exploration with General Function Approximation. Forty-First International Conference on Machine Learning.
  24. Zhang, W., Fan, Z., He, J., & Gu, Q. (2024). Achieving Constant Regret in Linear Markov Decision Processes. The Thirty-Eighth Annual Conference on Neural Information Processing Systems.
  25. Huang, Z., Hwang, J., Zhang, J., Baik, J., Zhang, W., Wodarz, D., Sun, Y., Gu, Q., & Wang, W. (2024). Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems. Proceedings of the ACM on Web Conference 2024, 4607–4617.
  26. Lopez, V. K., Cramer, E. Y., Pagano, R., Drake, J. M., O’Dea, E. B., Adee, M., Ayer, T., Chhatwal, J., Dalgic, O. O., Ladd, M. A., & others. (2024). Challenges of COVID-19 Case Forecasting in the US, 2020–2021. PLoS Computational Biology, 20(5), e1011200.
  27. Hoar, B. B., Zhang, W., Chen, Y., Sun, J., Sheng, H., Zhang, Y., Chen, Y., Yang, J. Y., Costentin, C., Gu, Q., & others. (2024). Redox-Detecting Deep Learning for Mechanism Discernment in Cyclic Voltammograms of Multiple Redox Events. ACS Electrochemistry, 1(1), 52–62.
  28. Sheng, H., Sun, J., Rodrı́guez Oliver, Hoar, B. B., Zhang, W., Xiang, D., Tang, T., Hazra, A., Min, D. S., Doyle, A. G., & others. (2024). Autonomous closed-loop mechanistic investigation of molecular electrochemistry via automation. Nature Communications, 15(1), 2781.
  29. Zhang, W., He, J., Fan, Z., & Gu, Q. (2023). On the interplay between misspecification and sub-optimality gap in linear contextual bandits. International Conference on Machine Learning, 41111–41132.
  30. Shea, K., Borchering, R. K., Probert, W. J. M., Howerton, E., Bogich, T. L., Li, S.-L., van Panhuis, W. G., Viboud, C., Aguás, R., Belov, A. A., & others. (2023). Multiple models for outbreak decision support in the face of uncertainty. Proceedings of the National Academy of Sciences, 120(18), e2207537120.
  31. Zhang, J., Zhang, W., & Gu, Q. (2023). Optimal horizon-free reward-free exploration for linear mixture mdps. International Conference on Machine Learning, 41902–41930.
  32. Zhang, W., Wang, X., Nie, W., Eaton, J., Rees, B., & Gu, Q. (2023). MoleculeGPT: Instruction Following Large Language Models for Molecular Property Prediction. NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development.
  33. Zhang, W., He, J., Zhou, D., Gu, Q., & Zhang, A. (2023). Provably efficient representation selection in low-rank Markov decision processes: from online to offline RL. Uncertainty in Artificial Intelligence, 2488–2497.
  34. Zhang, W., Wang, X., Smith, J., Eaton, J., Rees, B., & Gu, Q. (2023). Diffmol: 3d structured molecule generation with discrete denoising diffusion probabilistic models. ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling.
  35. Deng, Y., Zhang, W., Chen, Z., & Gu, Q. (2023). Rephrase and respond: Let large language models ask better questions for themselves. ArXiv Preprint ArXiv:2311.04205.
  36. Ji, K., Zhao, Q., He, J., Zhang, W., & Gu, Q. (2023). Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs. The Twelfth International Conference on Learning Representations.
  37. Hoar, B. B., Zhang, W., Xu, S., Deeba, R., Costentin, C., Gu, Q., & Liu, C. (2022). Electrochemical mechanistic analysis from cyclic voltammograms based on deep learning. ACS Measurement Science Au, 2(6), 595–604.
  38. Cramer, E. Y., Ray, E. L., Lopez, V. K., Bracher, J., Brennen, A., Rivadeneira, A. J. C., Gerding, A., Gneiting, T., House, K. H., Huang, Y., & others. (2022). Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States. Proceedings of the National Academy of Sciences, 119(15), e2113561119.
  39. Jia, Y., Zhang, W., Zhou, D., Gu, Q., & Wang, H. (2021). Learning Neural Contextual Bandits through Perturbed Rewards. International Conference on Learning Representations.
  40. Bracher, J., Wolffram, D., Deuschel, J., Görgen, K., Ketterer, J. L., Ullrich, A., Abbott, S., Barbarossa, M. V., Bertsimas, D., Bhatia, S., & others. (2021). A pre-registered short-term forecasting study of COVID-19 in Germany and Poland during the second wave. Nature Communications, 12(1), 5173.
  41. Zhang, W., Zhou, D., & Gu, Q. (2021). Reward-free model-based reinforcement learning with linear function approximation. Advances in Neural Information Processing Systems, 34, 1582–1593.
  42. Ray, E. L., Wattanachit, N., Niemi, J., Kanji, A. H., House, K., Cramer, E. Y., Bracher, J., Zheng, A., Yamana, T. K., Xiong, X., & others. (2020). Ensemble forecasts of coronavirus disease 2019 (COVID-19) in the US. MedRXiv, 2020–2008.
  43. Zhang, W., Zhou, D., Li, L., & Gu, Q. (2020). Neural Thompson Sampling. International Conference on Learning Representations.
  44. Zou, D., Wang, L., Xu, P., Chen, J., Zhang, W., & Gu, Q. (2020). Epidemic model guided machine learning for COVID-19 forecasts in the United States. MedRxiv, 2020–2005.
  45. Wu, Y. F., Zhang, W., Xu, P., & Gu, Q. (2020). A finite-time analysis of two time-scale actor-critic methods. Advances in Neural Information Processing Systems, 33, 17617–17628.
  46. Liu, S., Zhang, W., Wu, X., Feng, S., Pei, X., & Yao, D. (2018). A simulation system and speed guidance algorithms for intersection traffic control using connected vehicle technology. Tsinghua Science and Technology, 24(2), 160–170.