Tian Liu Chinese Name


Hi there! I am a third-year PhD student in the Computer Vision Lab and InfoLab in the Department of Computer Science and Engineering at Texas A&M University, co-advised by Prof. Shu Kong and Prof. James Caverlee. My research focuses on solving problems at the intersection of vision and language. Previously, I earned my master's degrees in Computer Science and Petroleum Engineering at Texas A&M. I have worked as a Measurement Engineer for Schlumberger (2019-2020) and later interned as a System Software Engineer at HPE (2021, 2022), and as a Research Intern at VISA Research (2025).

Email  /  Google Scholar  /  LinkedIn  /  Github

profile photo

News

Research

My research focuses on computer vision with Vision Language Models, addressing a central question: "how to adapt pretrained foundation models to better serve specific downstream tasks, with none or limited labeled data?". This question drives my efforts to identify and analyze the limitations of foundation models, examining their pretraining data to understand the origins of these limitations. My prior work includes developing advanced prompting and retrieval-augmented learning techniques for zero-shot recognition, as well as stage-wise retrieval-augmented finetuning methods for few-shot recognition. I am also exploring the application of foundation models for video understanding, with specific interests in detecting unusual activities, such as failure actions or behaviors indicative of autism in children.

In addition, I have broad interest in cyber-physical systems, including developing efficient machine learning systems on resource-constrained edge devices. Applications include efficient vision system for precision residential irrigation and voice assistance system for emergency medical services.

Beyond these areas, my research extends to machine learning for healthcare and geoscience. This includes developing safe reinforcement learning algorithms for personalized medicine; enhancing the fairness of cardiovascular disease (CVD) risk prediction models for underrepresented populations; advancing geoscientific methods for characterizing subsurface fracture distribution and integrating 4D seismic data for more accurate reservoir model calibration.



Robust Few-Shot Vision-Language Model Adaptation

Hanxin Wang*, Tian Liu* (*co-first authors), Shu Kong

arxiv / website / code

We proposed robust few-shot adaptation of VLM towards improved ID and OOD generalization via exploiting retrieval-augmented learning and stage-wise adversarial finetuning, achieving SOTA ID and OOD performance on standard OOD benchmarks.

Robust Rainfall Estimation with Multimodal Sensing for Precision Residential Irrigation

Tian Liu, Liuyi Jin, Radu Stoleru, Amran Haroon, Charles Swanson, Kexin Feng

[ACM Transactions on Sensor Networks (TOSN) 2025]  

paper / code

We developed low-cost, robust, privacy-preserving rainfall sensing system using multimodal data (visual recordings and audios from doorbell cameras), significantly improving SOTA irrigation systems with more accurate rainfall estimation.

Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning

Tian Liu, Huixin Zhang, Shubham Parashar, Shu Kong
[CVPR 2025, 4th CVinW and FGVC12 workshops]

arxiv / website / poster / code

We explore retrieval-augmented learning for solving few-shot recognition, and propose stage-wise retrieval-Augmented fineTuning (SWAT) method to mitigate the imbalanced distribution and domain gap issues, outperforming SOTA methods by >6% accuracy.

UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark

Hasnat Md Abdullah, Tian Liu, Kangda Wei, Shu Kong, Ruihong Huang
[WACV 2025]

arxiv / poster / code

We explore multimodal foundation models for Unusual Activities Localization (UAL) in video data. We compiled the first UAL benchmark dataset and proposed VLM-LLM framework to synergize multimodal foundational models for better video understanding.

ERIC: Estimating Rainfall with Commodity Doorbell Camera for Precision Residential Irrigation

Tian Liu, Liuyi Jin, Radu Stoleru, Amran Haroon, Charles Swanson, Kexin Feng

[ACM BuildSys 2024]   Best paper award / TPC praise

paper / arxiv / video presentation / slides / code / TAMU CSE Media Coverage
Texas A&M Engineering News / ASEE First Bell's newsletter

We develop efficient vision system to estimate hyperlocal rainfall from doorbell camera for precision residential irrigation, saving > 9,000 gallons of water per month.

The Neglected Tails in Vision-Language Models

Shubham Parashar*, Zhiqiu Lin*, Tian Liu* (*co-first authors), Xiangjue Dong, Yanan Li, Deva Ramanan, James Caverlee, Shu Kong
[CVPR 2024, ICML 2024 DMLR Workshop Oral]

paper / DMLR / arxiv / website / poster / code

We expose the long-tailed concept distributions in VLMs' pretraining data and reveal failues of SOTA multimodal systems (e.g. GPT-4V, DALL-E 3). We propose retrieval-augmented learning, achieving SOTA zero-shot recognition performance.

EMSAssist: An End-to-End Mobile Voice Assistant at the Edge for Emergency Medical Services

Liuyi Jin, Tian Liu, Amran Haroon, Radu Stoleru, Michael Middleton, Ziwei Zhu, Theodora Chaspari
[ACM MobiSys 2023]

paper / workshop paper / presentation / slides / app demo / code

We build the first end-to-end mobile voice assistant system to assist Emergency Medical Technicians in selecting proper protocols for critical medical intervention.

Safe Reinforcement Learning with Contextual Information: Theory and Applications

Junyu Cao*, Esmaeil Keyvanshokooh*, Tian Liu
[Under review]

preprint / code

We develop a safe reinforcement learning algorithm for personalized medical prescription considering patient's contextual information (e.g. age, gender, race etc.), achieveing sub-linear regret with zero safety violation.

A Machine Learning-based Hybrid Model for Fracture Parameterization and Distribution Prediction in Unconventional Reservoirs

Tian Liu, Ruxin Zhang
[Journal of Computers and Geotechnics 2024]  

paper

We develop Variational Autoencoder (VAE) model for fracture parameterization and distribution prediction using reservoir production data.

Integration of Time-lapse Seismic Data using the Onset Time Approach: the Impact of Seismic Survey Frequency

Tian Liu, Hongquan Chen, Gill Hetz, Akhil Datta-Gupta

[Journal of Petroleum Science and Engineering 2020]  

1st Place of TAMU Student Paper Contest, 3rd Place of International Championship

JPSE journal paper / ATCE paper

We develop onset-time approach for efficient and robust integration of 4D seismic data for reservoir model calibration, achieveing 2x error reduction and 6x speedup compared to traditional amplitude-matching methods.

Workshop Papers/Presentations

    (* denotes equal contribution)
  • T. Liu, H. Zhang, S. Parashar, S. Kong. "Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning." CVPR 2025 Workshop on Computer Vision in the Wild. Nashville, U.S, June 2025.
  • T. Liu, H. Zhang, S. Parashar, S. Kong. "Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning." CVPR 2025 Workshop on Fine-Grained Visual Categorization. Nashville, U.S, June 2025.
  • Y. Yang*, T. Liu*, S. J. Lee, C.-Y. Liao, H. Shao, F. Pasquel, M. B. Weber, E. Keyvanshokooh, G.-G. P. Garcia. "Development and Fairness Evaluation of CVD Risk Prediction Models for Patients with Type-2 Diabetes." Society for Medical Decision Making Annual Meeting, Boston, MA, October 2024. Poster
  • Y. Yang*, T. Liu*, S. J. Lee, C.-Y. Liao, H. Shao, F. Pasquel, M. B. Weber, E. Keyvanshokooh, G.-G. P. Garcia. "Survival Modeling for CVD Risk Estimation Among a Diverse Cohort with Type-2 Diabetes." AI for Health Equity Symposium AIM-AHEAD Annual Meeting, Atlanta, GA, August 2024.
  • S. Parashar*, Z. Lin*, T. Liu*, X. Dong, Y. Li, D. Ramanan, J. Caverlee, and S. Kong, "The Neglected Tails in Vision-Language Models." ICML 2024 Workshop on Data-centric Machine Learning Research (DMLR): Datasets for Foundation Models, Vienna, Austria, July 2024.
  • L. Jin, T. Liu, A. Haroon, R. Stoleru, M. Middleton, Z. Zhu, T. Chaspari, "Demo: EMSAssist -- An End-to-End Mobile Voice Assistant at the Edge for Emergency Medical Services." The 21st IEEE International Conference on Mobile Systems, Applications and Services (MobiSys), 2023, Helsinki, Finland, June 2023.

Teaching Assistance

  • CSCE606: Software Engineering, Fall 2025
  • CSCE670: Information Storage and Retrieval, Spring 2025
  • CSCE606: Software Engineering, Fall 2023
  • CSCE313: Introduction to Computer Systems, Summer 2023
  • CSCE110: Programming I, Summer 2023

Professional Services

  • Coordinator of 5th Open World Vision Workshop at CVPR'25.
  • Coordinator of 4th Open World Vision Workshop at CVPR'24.
  • Reviewer for Pattern Recognition, WACV'25, ICLR'25 FM-Wild Workshop, ICCV'25, NeurIPS'25
  • Reviewer for IEEE Internet of Things Journal
  • Reviewer for Applied Thermal Engineering, Geoenergy Science and Enginerring, SPE Journal

Selected Awards

  • TAMU CSE Department Travel Grant, 2025
  • ACM BuildSys, Best Paper Award, 2024
  • TAMU CSE Department Travel Grant, 2024
  • TAMU CSE Department Graduate Teaching Assistant Excellence Award (1 each year), 2024
  • 1st place of SPE Student Paper Contest in TAMU, 1st place of Gulf Coast Region, 3rd place of International Championship, 2018
  • 2nd place of SPE Petrobowl Knowledge Contest in North American Region, 2017
  • 1st place of SPE Petrobowl Knowledge Contest in Asia-Pacific Region, 2015
  • Dean's Award (4 out of 296), China University of Petroleum Beijing, 2014
  • National Scholarship, Ministry of Education of China, 2012

Miscellaneous


Template modified from Jon Barron