Zhi-ning Liu (刘芷宁)

News

Education

University of Illinois Urbana-Champaign

Ph.D. in Computer Science · 2022 - 2026 (expected)

Department of Computer Science · Advisor: Prof. Hanghang Tong

Jilin University

M.Eng. in Computer Science · 2019 - 2022

School of Artificial Intelligence · Advisor: Prof. Yi Chang

B.Sc. in Computer Science · 2015 - 2019

Tang-Aoqing Honors Program · Computer Science

Experience

Amazon

Applied Scientist Intern · Palo Alto, CA · May - Dec 2025

Amazon Ads · Vision language model reasoning reliability -> ICLR 2026, ICML 2026, ACL 2026

Applied Scientist Intern · Palo Alto, CA · May - Aug 2024

Amazon Rufus · RAG-based language model reasoning -> ACL 2025

Applied Scientist Intern · Seattle, WA · May - Aug 2023

Amazon Search · Multi-task learning for partially ordered entity ranking

Microsoft Research

Research Intern · Beijing · Aug 2018 - June 2019

Machine Learning Group · Extreme class-imbalanced learning -> ICDE 2020, NeurIPS 2020

Publications

Publications, preprints, and submissions, sorted by year. See the full list on Google Scholar.

• ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
  Y Zhao, R Qiu, T Wei, Y Bei, Z Liu, L Chen, I Lourentzou, H Tong, J He
  arXiv preprint arXiv:2607.02509, 2026
  Scholar
  LLMHarness
• AdaFuse: Adaptive Ensemble Decoding for Large Language Models
  C Cui, T Wei, Z Chen, R Qiu, Z Zeng, Z Liu, X Ning, D Zhou, J He
  Proceedings of the 64th Annual Meeting of the Association for Computational …, 2026
  Scholar
  LLMEnsemble
• Mem-gallery: Benchmarking multimodal long-term conversational memory for mllm agents
  Y Bei, T Wei, X Ning, Y Zhao, Z Liu, X Lin, Y Zhu, H Hamann, J He, ...
  Proceedings of the 64th Annual Meeting of the Association for Computational …, 2026
  Scholar
  LLMAgentMultimodalBenchmarking
• Code as agent harness
  X Ning, K Tieu, D Fu, T Wei, Z Li, Y Bei, J Zou, M Ai, Z Liu, TW Li, L Chen, ...
  arXiv preprint arXiv:2605.18747, 2026
  Scholar
  LLMAgentHarness
• Continual low-rank adapters for llm-based generative recommender systems
  H Yoo, TW Li, SK Kang, Z Liu, CC Xu, Q Qi, H Tong
  International Conference on Learning Representations 2026, 6618-6642, 2026
  Scholar
  LLMRecommender-Systems
• Seeing but not believing: Probing the disconnect between visual attention and answer correctness in vlms
  Z Liu, Z Chen, H Liu, C Luo, X Tang, S Wang, J Zeng, Z Dai, Z Shi, T Wei, ...
  International Conference on Learning Representations 2026, 72849-72876, 2026
  Scholar
  Trustworthy-AIMultimodal
• Planetalign: A comprehensive python library for benchmarking network alignment
  Q Yu, Z Zeng, Y Yan, Z Liu, B Jing, R Qiu, A Azad, H Tong
  International Conference on Learning Representations 2026, 66087-66115, 2026
  Scholar
  Trustworthy-AIGraphBenchmarkingFairness
• Language in the flow of time: Time-series-paired texts weaved into a unified temporal narrative
  Z Li, X Lin, Z Liu, J Zou, Z Wu, L Zheng, D Fu, Y Zhu, H Hamann, H Tong, ...
  International Conference on Learning Representations 2026, 24437-24484, 2026
  Scholar
  Time-Series
• Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
  X Lin, Z Tang, W Cong, M Hang, K Wang, Y Wang, Z Zeng, TW Li, H Yoo, ...
  Proceedings of the ACM Web Conference 2026, 6469-6480, 2026
  Scholar
  EnsembleRecommender-Systems
• ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
  R Qiu, H Zeng, Y Xia, Y Meng, R Chen, J Feng, D Fu, Q Wang, J Liu, ...
  arXiv preprint arXiv:2603.10160, 2026
  Scholar
  LLMEnsemble
• Flow matching meets biology and life science: a survey
  Z Li, Z Zeng, X Lin, F Fang, Y Qu, Z Xu, Z Liu, X Ning, T Wei, G Liu, H Tong, ...
  npj Artificial Intelligence 2 (1), 17, 2026
  Scholar
• Agentic reasoning for large language models
  T Wei*, TW Li*, Z Liu*, X Ning, Z Yang, J Zou, Z Zeng, R Qiu, X Lin, D Fu, ...
  arXiv preprint arXiv:2601.12538, 2026
  Scholar
  LLMAgent
• Adafuse: Adaptive ensemble decoding with test-time scaling for llms
  C Cui, T Wei, Z Chen, R Qiu, Z Zeng, Z Liu, X Ning, D Zhou, J He
  arXiv preprint arXiv:2601.06022, 2026
  Scholar
  LLMEnsemble
• Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
  Z Liu, T Wang, X Lin, P Ouyang, G Li, Z Yang, H Liu, S Keswani, ...
  Findings of the Association for Computational Linguistics: ACL 2026, 2026
  Scholar
  LLMTrustworthy-AIMultimodalFairness
• ClimateBench-M: a multi-modal climate data benchmark with a simple generative method
  D Fu, Y Zhu, Z Liu, L Zheng, X Lin, Z Li, L Fang, K Tieu, O Bhardwaj, ...
  Proceedings of the 34th ACM International Conference on Information and …, 2025
  Scholar
  MultimodalBenchmarking
• Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity.
  Z Li, F Fang, X Zhang, J Zou, Z Liu, W Xiong, Z Wu, B Jing, J He
  EMNLP (Findings), 3426-3455, 2025
  Scholar
  LLMTrustworthy-AIFairness
• Hierarchical lora moe for efficient ctr model scaling
  Z Zeng, M Hang, X Liu, X Liu, X Lin, R Qiu, T Wei, Z Liu, S Yuan, C Yang, ...
  arXiv preprint arXiv:2510.10432, 2025
  Scholar
  LLMEnsemble
• Llm-recg: A semantic bias-aware framework for zero-shot sequential recommendation
  Y Li, J Wang, H Sundaram, Z Liu
  Proceedings of the nineteenth ACM conference on recommender systems, 237-246, 2025
  Scholar
  LLMTrustworthy-AIFairnessRecommender-Systems
• Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
  Z Liu, Z Yang, X Lin, R Qiu, T Wei, Y Zhu, H Hamann, J He, H Tong
  Proceedings of the 42nd International Conference on Machine Learning 267 …, 2025
  Scholar
  Time-SeriesEnsemble
• MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
  X Lin*, Z Liu*, Z Yang*, G Li, R Qiu, S Wang, H Liu, H Li, S Keswani, ...
  arXiv preprint arXiv:2505.14728, 2025
  Scholar
  LLMTrustworthy-AIMultimodalBenchmarkingFairness
• Cats: Mitigating correlation shift for multivariate time series classification
  X Lin, Z Zeng, T Wei, Z Liu, H Tong
  arXiv preprint arXiv:2504.04283, 2025
  Scholar
  Time-Series
• SelfElicit: Your language model secretly knows where is the relevant evidence
  Z Liu, RA Amjad, R Adkathimar, T Wei, H Tong
  Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025
  Scholar
  LLM
• TRQA: time series reasoning question and answering benchmark
  B Jing, S Chen, L Zheng, B Liu, Z Li, J Zou, T Wei, Z Liu, Z Zeng, R Qiu, ...
  Google Scholar entry, 2025
  Scholar
  Time-SeriesBenchmarking
• CLIMB: Class-imbalanced learning benchmark on tabular data
  Z Liu, Z Li, Z Yang, T Wei, J Kang, Y Zhu, H Hamann, J He, H Tong
  Advances in Neural Information Processing Systems 38, 2025
  Scholar
  BenchmarkingClass-Imbalance
• Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation
  W Bao, Z Zeng, Z Liu, H Tong, J He
  The Thirteenth International Conference on Learning Representations, 2025
  Scholar
  Graph
• Thegcn: Temporal heterophilic graph convolutional network
  Y Yan, Y Chen, H Chen, X Li, Z Xu, Z Zeng, L Liu, Z Liu, H Tong
  arXiv preprint arXiv:2412.16435, 2024
  Scholar
  GraphTime-Series
• Backtime: Backdoor attacks on multivariate time series forecasting
  X Lin, Z Liu, D Fu, R Qiu, H Tong
  Advances in Neural Information Processing Systems 37, 131344-131368, 2024
  Scholar
  Trustworthy-AITime-Series
• Wapiti: A watermark for finetuned open-source llms
  L Chen, R Qiu, S Yuan, Z Liu, T Wei, H Yoo, Z Zeng, D Yang, H Tong
  arXiv preprint arXiv:2410.06467, 2024
  Scholar
  LLMTrustworthy-AI
• AIM: Attributing, interpreting, mitigating data unfairness
  Z Liu, R Qiu, Z Zeng, Y Zhu, H Hamann, H Tong
  Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and …, 2024
  Scholar
  Trustworthy-AIFairness
• Graph mixup on approximate gromov–wasserstein geodesics
  Z Zeng, R Qiu, Z Xu, Z Liu, Y Yan, T Wei, L Ying, J He, H Tong
  Forty-first International Conference on Machine Learning, 2024
  Scholar
  Graph
• Group fairness via group consensus
  E Chan*, Z Liu*, R Qiu, Y Zhang, R Maciejewski, H Tong
  Proceedings of the 2024 ACM Conference on Fairness, Accountability, and …, 2024
  Scholar
  Trustworthy-AIFairness
• Ensuring user-side fairness in dynamic recommender systems
  H Yoo, Z Zeng, J Kang, R Qiu, D Zhou, Z Liu, F Wang, C Xu, E Chan, ...
  Proceedings of the ACM web conference 2024, 3667-3678, 2024
  Scholar
  Trustworthy-AIFairnessRecommender-Systems
• Hierarchical multi-marginal optimal transport for network alignment
  Z Zeng, B Du, S Zhang, Y Xia, Z Liu, H Tong
  Proceedings of the AAAI Conference on Artificial Intelligence 38 (15), 16660 …, 2024
  Scholar
  Trustworthy-AIGraphFairness
• Class-Imbalanced Graph Learning without Class Rebalancing
  Z Liu, R Qiu, Z Zeng, H Yoo, D Zhou, Z Xu, Y Zhu, K Weldemariam, J He, ...
  Forty-first International Conference on Machine Learning, 2024
  Scholar
  GraphClass-Imbalance
• Taming over-smoothing representation on heterophilic graphs
  K Guo, X Cao, Z Liu, Y Chang
  Information Sciences 647, 119463, 2023
  Scholar
  Graph
• Web-based long-term spine treatment outcome forecasting
  H Ye*, Z Liu*, W Cao, AM Amiri, J Bian, Y Chang, JD Lurie, J Weinstein, ...
  Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and …, 2023
  Scholar
  Time-Series
• Uadb: Unsupervised anomaly detection booster
  H Ye*, Z Liu*, X Shen, W Cao, S Zheng, X Gui, H Zhang, Y Chang, J Bian
  2023 IEEE 39th International Conference on Data Engineering (ICDE), 2593-2606, 2023
  Scholar
• A survey of explainable graph neural networks for cyber malware analysis
  D Warmsley, A Waagen, J Xu, Z Liu, H Tong
  2022 IEEE international conference on big data (Big Data), 2932-2939, 2022
  Scholar
  Trustworthy-AIGraph
• Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning
  Z Wei, Y Wang, J Li, Z Liu, E Yu, Y Tian, X Wang, Y Chang
  Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the …, 2022
  Scholar
  Graph
• Handling inter-class and intra-class imbalance in class-imbalanced learning
  Z Liu, P Wei, Z Wei, B Yu, J Jiang, W Cao, J Bian, Y Chang
  arXiv preprint arXiv:2111.12791, 2021
  Scholar
  Class-Imbalance
• IMBENS: Ensemble class-imbalanced learning in Python
  Z Liu, J Kang, H Tong, Y Chang
  arXiv preprint arXiv:2111.12776, 2021
  Scholar
  EnsembleClass-Imbalance
• Self-paced ensemble for highly imbalanced massive data classification
  Z Liu, W Cao, Z Gao, J Bian, H Chen, Y Chang, TY Liu
  2020 IEEE 36th international conference on data engineering (ICDE), 841-852, 2020
  Scholar
  EnsembleClass-Imbalance
• MESA: boost ensemble imbalanced learning with meta-sampler
  Z Liu, P Wei, J Jiang, W Cao, J Bian, Y Chang
  Advances in neural information processing systems 33, 14463-14474, 2020
  Scholar
  EnsembleClass-Imbalance
• Reinforcement Routing for Mixtures of LoRAs in Parameter-Efficient LLM Finetuning
  R Qiu, H Zeng, Y Xia, J Feng, Y Meng, R Chen, D Fu, Q Wang, J Liu, ...
  Google Scholar entry
  Scholar
  LLMEnsemble
• Inference Scaling of LLM Ensembling: Bridging Token Spaces with Token Translation
  T Wei, Z Zeng, R Qiu, Z Liu, X Ning, X He, W Bao, Q He, X Tang, H Tong, ...
  Google Scholar entry
  Scholar
  LLM

Selected Awards & Honors

Fun Facts