Tianci Liu

portrait.png

I am an incoming assistant professor in EECS at the University of Tennessee, Knoxville. I am wrapping up my Ph.D. in ECE at Purdue, advised by Prof. Jing Gao.

My research focuses on knowledge-centric AI. I am broadly interested in building efficient, reliable, and adaptive AI systems that can acquire and integrate knowledge to better understand the world (ACL’25, ICML’25, ICLR’25), human needs (ECCV’26, ICML’26, ACL’26), and societal contexts (ICML’24, ICLR’24, AAAI’23) with minimal supervision.

📢 I am excited to recruit students for two fully funded Ph.D. positions starting in Spring 2027, working on Artificial Intelligence, Machine Learning, and Natural Language Processing. I also warmly welcome applications from students interested in research internships. If you are interested in joining my group, I would love to hear from you! Please complete this form and then send me a brief email at tliu43 [at] utk.edu. I look forward to learning more about you!

news

Nov 23, 2025 Our paper “PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers” was accepted at KDD’26 Research Track.
Sep 21, 2025 Our paper “Toward Multimodal, General-Purpose, and Generalizable Knowledge Editing for Foundation Models” was accepted at ICDM’25 BlueSky Track.
Aug 20, 2025 Our paper “Towards Universal Debiasing for Language Models-based Tabular Data Generation” and “Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs” were accepted at EMNLP’25 Findings.
May 15, 2025 Our paper “RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization” was accepted at ACL’25 Findings.
May 08, 2025 Our paper “RAM-Hand: Robust Acoustic Multi-Hand Pose Reconstruction Using a Microphone Array” won Best Paper Award at Sensys’25.

selected publications

  1. ECCV’26
    Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
    Tianci Liu, Zihan Dong, Linjun Zhang, and 5 more authors
    In The Nineteenth European Conference on Computer Vision, 2026
  2. ICML’26
    Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
    Ran Xu*, Tianci Liu*, Zihan Dong, and 6 more authors
    In The Fourty-Third International Conference on Machine Learning, 2026
  3. ACL’26
    OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
    Tianci Liu*, Ran Xu*, Tony Yu, and 4 more authors
    In The 64th Annual Meeting of the Association for Computational Linguistics, 2026
  4. ACL’25 Findings
    RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization
    Tianci Liu*, Haoxiang Jiang*, Tianze Wang, and 5 more authors
    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
  5. ICML’25
    Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
    Tianci Liu, Ruirui Li, Zihan Dong, and 6 more authors
    In The Fourty-Second International Conference on Machine Learning, 2025
  6. ICLR’25
    Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
    Tianci Liu, Ruirui Li, Yunzhe Qi, and 8 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
  7. EMNLP’24
    RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
    Haoyu Wang, Tianci Liu, Ruirui Li, and 3 more authors
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
    Oral Paper