Short Bio

I am a PhD student at the CMU-CleaR group at Carnegie Mellon University, supervised by Prof. Kun Zhang. I have been engaged in AI research since 2018. Previously, I was a Machine Learning Engineer at Apple AI/ML. I received my Master's degree in Electronic Information from Nanjing University in 2025, supervised by Prof. Chunlin Chen, IEEE Fellow, and my Bachelor's degree in Software Engineering from Wuhan University of Technology in 2022. I also spent wonderful times as a research intern at Microsoft Research and Alibaba Group.

Research Interests

I focus on the following research topics:

• Foundation (Language) Models
• Representation Learning
• Reinforcement Learning

Especially in applications to multiple sequences and dynamic environments, enabling them to adapt to non-stationary distributions in the real world explicitly. Currently, I am working on next-generation foundation models.

Work Experience

• Apple, AI/ML, Machine Learning Engineer, ICT 3 (07/2025 - 08/2026)
  Worked on World Knowledge Search for Siri AI, worked with Dr. Zheng Sun and Dr. Ruofei Zhang.
• Microsoft Research Asia, Industry Innovation Center, Research Intern (10/2024 - 06/2025)
  Explored Overfitting and Data Efficiency in LLM Optimization, advised by Dr. Jiang Bian.
• Microsoft Research Asia, Machine Learning Area, Research Intern (11/2023 - 05/2024)
  Worked on XAI and RL for Large Language Models, advised by Dr. Lei Song.
• Alibaba Group, DAMO & Alibaba Cloud, Research Intern (06/2023 - 11/2023)
  Worked on XAI for Time Series, advised by Dr. Qingsong Wen.

Publications

* indicates equal contribution, ^† indicates corresponding author. Please see my full list at Google Scholar Profile.

Journals

• [3] Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning
  Z. Liu, X. Yang, Z. Liu, Y. Xia, W. Jiang, Y. Zhang, L. Li, G. Fan, L. Song, J. Bian
  Transactions on Machine Learning Research (TMLR), 2025
• [2] MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees
  Z. Liu, Y. Zhu, Z. Wang, Y. Gao, C. Chen
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
• [1] Spatial-Temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
  Z. Liu, R. Zhang, C. Wang, Z. Xiao, H. Jiang
  IEEE Transactions on Network Science and Engineering (TNSE), 2022

Conferences

• [11] On the Effect of Sampling Diversity in Scaling LLM Inference
  T. Wang*, Y. Chen*, Z. Liu*, J. Light, H. Chen, X. Zhang, W. Cheng
  Conference on Uncertainty in Artificial Intelligence (UAI), 2026
• [10] Time-RA: Towards Time Series Reasoning for Anomaly with LLM Feedback
  Y. Yang*, Z. Liu*, L. Song, K. Ying, Z. Wang, T. Bamford, S. Vyetrenko, J. Bian, Q. Wen
  Association for Computational Linguistics (ACL), 2026
• [9] Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
  T. Wang, Y. Chen, Z. Liu, Z. Chen, H. Chen, X. Zhang, W. Cheng
  International Conference on Learning Representations (ICLR), 2025
• [8] Protecting Your LLMs with Information Bottleneck
  Z. Liu, Z. Wang, L. Xu, J. Wang, L. Song, T. Wang, C. Chen, W. Cheng, J. Bian
  Conference on Neural Information Processing Systems (NeurIPS), 2024
• [7] TimeX++: Learning Time-Series Explanations with Information Bottleneck
  Z. Liu, T. Wang, J. Shi, X. Zheng, Z. Chen, L. Song, W. Dong, J. Obeysekera, F. Shirani, D. Luo
  International Conference on Machine Learning (ICML), 2024
• [6] Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
  Y. Xia, X. Yang, Z. Liu, Z. Liu, L. Song, J. Bian
  International Conference on Machine Learning (ICML Oral), 2024
• [5] Explaining Time Series via Contrastive and Locally Sparse Perturbations
  Z. Liu, Y. Zhang, T. Wang, Z. Wang, D. Luo, M. Du, M. Wu, Y. Wang, C. Chen, L. Fan, Q. Wen
  International Conference on Learning Representations (ICLR), 2024
• [4] RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
  Z. Wang*, Z. Liu*, Y. Zhang, A. Zhong, L. Fan, L. Wu, Q. Wen
  Conference on Information and Knowledge Management (CIKM), 2024
• [3] Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
  L. Xu, Z. Liu, A. Dockhorn, D. Perez-Liebana, J. Wang, L. Song, J. Bian
  IEEE Conference on Games (CoG), 2024
• [2] NA2Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
  Z. Liu, Y. Zhu, C. Chen
  International Conference on Machine Learning (ICML), 2023
• [1] Multi-View Spatial-Temporal Model for Travel Time Estimation
  Z. Liu, Z. Wu, M. Wang, R. Zhang
  International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2021

PrePrints

• [5] Tool-Adaptive LLM Reranker
  Z. Liu^†, R. Hua
  arXiv:2607.10555, 2026
• [4] Diversified Scaling Inference in Time Series Foundation Models
  R. Hua, Z. Liu^†, K. Zhang, Y. Yang
  arXiv:2601.17376, 2026
• [3] Sample-efficient LLM Optimization with Reset Replay
  Z. Liu, J. Wang, L. Song, J. Bian
  arXiv:2508.06412, 2025
• [2] Towards A Unified Information Bottleneck Framework for Time Series Explanations
  X. Zheng*, Z. Liu*, Z. Chen, M. Akewar, J. Bhimani, J. Liu, M. Sha, J. Ni, W. Cheng, D. Luo
  Under Review
• [1] Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative MARL
  Y. Zhu, Q. Zhao, Z. Liu, Z. Wang, C. Chen
  arXiv:2305.07182, 2023

Invited Talks

• 2026.07, Alumni sharing on R&D talent open day, Apple.
• 2024.04, Invited talk on perturbation for explaining sequence predictions, Microsoft Research Asia.
• 2024.02, Invited talk on interpretable and efficient multi-agent reinforcement learning, Nanjing University.

Honors & Awards

• 2026, CMU PhD Fellowship.
• 2025, Outstanding Master's Thesis, Nanjing University.
• 2025, China National Scholarship.
• 2023, 2024, First-Class Scholarship, Nanjing University.
• 2022, Outstanding Graduate, Wuhan University of Technology.
• 2020, 2021, First-Class Scholarship, Wuhan University of Technology.
• 2021, Kaggle Competitions Expert, Ranking Top 757th/213,123.
• 2021.08, Second Runner-up (Top 4th / 1295), ACM SIGSPATIAL GISCUP (2,500 USD).
• 2020.08, National 2nd Place (Top 2nd / 4133), China Collegiate Computing Contest (10,000 CNY).
• 2020.01, DSB Student Award (Top 1% & UP2ND), Kaggle Data Science Bowl (3,000 USD).
• 2020.10, National Second Prize, China Undergraduate Mathematical Contest in Modeling.

Mentoring

• Ruijin Hua (Fall 2025 - Present), B.S., Huazhong University of Science and Technology.

Professional Services

• Reviewer of NeurIPS 2024, 2025, and 2026.
• Reviewer of ICML 2025 and 2026.
• Reviewer of ICLR 2025 and 2026.
• Reviewer of AAAI 2025, 2026, and 2027.
• Reviewer of AISTATS 2025.
• Reviewer of CIKM 2025.
• Reviewer of ACL 2026.
• Reviewer of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
• Reviewer of IEEE Transactions on Network Science and Engineering (TNSE).
• Reviewer of IEEE Transactions on Computational Social Systems (TCSS).