Trustworthy and Reliable AI Lab (TRAIL Lab)
Embedded Files
Ruixiang (Ryan) Tang
Department of Computer Science
Rutgers-New Brunswick
Address: 110 Frelinghuysen Rd, Hill Center 416, Piscataway, NJ 08854
Email: ruixiang.tang@rutgers.edu
About Our Lab
I am a Tenure-Track Assistant Professor in the Department of Computer Science at Rutgers University–New Brunswick. I received my Ph.D. in Computer Science from Rice University, where I was advised by Dr. Xia Hu. I began my undergraduate studies in Biology at Tsinghua University, conducting research under the guidance of Dr. Xu Tan, and later transferred to the Department of Automation, completing my B.S. under the supervision of Dr. Jiwen Lu.
My group, the Trustworthy and Reliable AI Lab (TRAIL), works on Trustworthy AI, with the goal of infusing trust throughout the AI lifecycle. We pursue this goal by formalizing trustworthiness objectives (e.g., robustness, interpretability, and safety) and developing principled algorithms with measurable guarantees and transparent failure modes. I also collaborate closely with biologists and health informaticians to translate trustworthy learning methods to high-impact problems in biology and medicine.
Large Foundation Models introduce new and complex trustworthiness challenges. Our long-term objective is to develop learning algorithms that improve reasoning reliability under distribution shift and adversarial manipulation, supported by theoretical frameworks that connect representation, optimization, and uncertainty to trust outcomes. By advancing the underlying reasoning mechanisms, we aim to make these models more reliable, transparent, and resistant to misuse.
🔥 I’m always looking for outstanding PhD students and research interns. If you’re interested, please email me with your CV, transcript, a summary of your research experience, and highlight publications. I will carefully review every application.
Research Overview
Operational Interpretability
Turning mechanistic insight into practical tools that monitor, audit, and steer model behavior once deployed.
Agentic Safety
Keeping autonomous and multiagent systems reliable through continuous auditing and early failure prediction.
Robust Perception
Hardening multimodal and embodied perception so it holds steady under adversarial attack and distribution shift.
AI for Biomedicine
Translating trustworthy learning into high-impact problems across biology and medicine with clinical and biological collaborators.
News
6/2026: I am pleased to be invited to give a talk at IBM on agent safety and early failure detection [Slides Link].
[award] 5/2026: We are honored to receive an AI Pilot Award from NIDDK through the PanKbase program. We thank the program leadership, and look forward to contributing to this important diabetes research community resource.
[award] 5/2026: Our ICME paper "Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Models" has been selected as a Best Paper Award candidate.
[paper] 4/2026: Two papers accepted to ICML 2026. We explored the actionable mechanistic interpretation of massive values in LLMs and proposed generalizable implicit In-Context Learning via attention routing.
4/2026: This summer, Boxuan and Yihao will be research interns at AMD, Zeru at NVIDIA, and Yufei at Genentech. Congratulations to all!
[paper] 4/2026: One paper accepted by ACL 2026, we develop a case-augmented alignment approach that improves LLM safety and reduces over-refusal compared to rule-based methods.
[award] 3/2026: We received AMD University Program: AI & HPC Cluster Allocation Award to support our research on AI agents and memory systems, thanks to AMD for their support!
[paper] 2/2026: One paper has been accepted at ICME 2026. We developed a framework to accurately predict the uncertainty of VLA models.
[paper] 2/2026: One paper has been accepted to CVPR 2026 Findings, we evaluate and enhance LLMs’ counterfactual reasoning ability for video understanding tasks.
[award] 1/2026: Our interdisciplinary project "AI–Geoscience Collaborations for a Changing Arctic" has been funded by the Rutgers SAS Research in Academic Themes. We look forward to advancing foundational results at the AI–Earth systems interface.
[paper] 1/2026: One paper accepted by ICLR 2026, we design a memory efficient LLM fine tuning method via instance-aware token ditching.
[paper] 1/2026: One paper accepted by EACL 2026, we provide FaithLM, an intervention-based framework that evaluates and improves LLM explanation faithfulness.
12/2025: I'm happy to serve as organizer for the ICME 2026 Special Session on “Trustworthy and Secure Vision-Language-Action Models: Foundations, Methods, and Evaluation.” Submissions are warmly welcome.
[paper] 11/2025: Three papers accepted to AAAI 2026 (two orals, one poster). Our work advances multimodal reasoning, improves reasoning efficiency, and explores counterfactual reasoning in LLMs.
[award] 10/2025: Congratulations to Zeru Shi for being selected as a Rutgers Climate and Energy Institute (RCEI) Fellowship!
[paper] 10/2025: One paper accepted by AACL 2025. We provide a dataset, taxonomy, and baselines for analysis of rational persuasion and manipulation.
[paper] 8/2025: Three paper (one main two findings) accepted by EMNLP 2025. We explored multimodal in-context learning, LoRA security, and an LLM agent for text style transfer.
[paper] 7/2025: One paper accepted by Bioinformatics Advances. We explored a LLM-based framework that improves rare disease gene prioritization through phenotype-driven classification.
[paper] 7/2025: One paper accepted by COLM 2025: we explored replacing multimodal examples with learnable vectors to improve in-context learning in Large Vision-Language Models.
[paper] 6/2025: Two papers accepted by ICCV 2025: we explored the robustness of Vision-Language-Action model-based robotics, and addressed hallucination in Large Vision-Language Models.
5/2025: Invited to serve as an Associate Editor for Smart Health.
[award] 5/2025: Congratulations to Leroy Souz for being named a Paul Robeson Centennial Scholar and for reaching the semifinals of the Rice Business Plan Competition.
[paper] 5/2025: Two papers accepted by ACL 2025 Main, we explored using explainability to detect backdoors in LLMs and disentangle reasoning from memory in LLMs.
[paper] 5/2025: One paper accepted by ICML 2025, we show that Massive Q/K values are key to contextual understanding in LLMs.
[paper] 4/2025: Our paper "Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond" is now the all-time most-read article of ACM Transactions on Knowledge Discovery from Data (TKDD)!
[award] 2/2025: Receive 2,000 $ API credit from OpenAI to support our research on detecting and mitigating hallucination in VLMs.
[paper] 2/2025: One paper accepted by SIGKDD Explorations, we proposed to mitigate shortcuts in natural language understanding tasks.
[paper] 1/2025: One paper accepted by ICLR 2025, we proposed MRT to efficiently edit multimodal representations.
1/2025: Our tutorial about "Understanding Large-Scale Machine Learning Robustness under Paradigm Shift" is accepted by SDM 2025. See you in Virginia!
[paper] 09/2024: Three papers have been accepted for EMNLP 2024, focusing on issues related to LLM intellectual property protection, bias mitigation, and building trustworthy agents.
[paper] 07/2024: Our paper, Mitigating Relational Bias on Knowledge Graphs, has been accepted by TKDD.
[award] 04/2024: Our paper, The Science of Detecting LLM-Generated Text, has been accepted for a cover paper in the April 2024 issue of Communications of the ACM (CACM)!
[award] 04/2024: Our research about AI for watermarking has been awarded the annual Hershel M. Rich Invention Award, congratulations to the team!
[paper] 03/2024: One paper has been accepted by the NAACL 2024. We proposed a key prompt protection mechanism to safeguard large language models.
[paper] 02/2024: One paper has been accepted by the Journal of Biomedical Informatics. We proposed a soft prompt calibration method to mitigate the variance of large language model output in the radiology report summarization task.
[paper] 01/2024: Our paper, Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond, has been accepted by TKDD.
[award] 10/2023: Our paper about using LLMs for patient-trial matching was selected as the AMIA 2023 Best Student Paper and KDDM Student Innovation Award.
[award] 10/2023: Our paper about building knowledge refinement and retrieval systems for interdisciplinarity in biomedical research has been selected as CIKM 2023 Best Demo Paper Honorable Mention.
[paper] 10/2023: One paper has been accepted by EMNLP 2023. We introduce a membership inference attack aimed at Large Language Models to analyze associated privacy risks.
[paper] 09/2023: Two papers have been accepted by NeurIPS 2023. We proposed a honeypot mechanism to defend against backdoor attacks in language models.
[paper] 08/2023: One paper has been accepted by ECML-PKDD 2023. We proposed a serial key protection mechanism for safeguarding DNN models.
[paper] 08/2023: Two papers have been accepted by CIKM 2023. We proposed a transferable watermark for defending against model extraction attacks.
[paper] 07/2023: Three Papers have been accepted by AMIA 2023 Annual Symposium. We investigated methods for harnessing the capabilities of LLMs in several healthcare tasks, such as Named Entity Recognition, Relation Extraction, and Patient-Trial Matching.
[paper] 05/2023: One paper has been accepted by ACL 2023. We reveal that LLMs are "lazy learners" that tend to exploit shortcuts in prompts for downstream tasks.
[paper] 04/2023: One paper has been accepted by SIGKDD Exploration 2023. We proposed a clean-label backdoor-based watermarking framework for safeguarding training datasets.
[paper] 03/2023: One paper has been accepted by ICHI 2023. We proposed a deep ensemble framework for improving phenotype prediction from multi-modal data.
Services
Area Chair/Program Committee Member / Reviewer:
Area Chair: ACL ARR
Conference: ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, ARR, IJCAI, AAAI, SDM, CIKM, etc.
Journal: PNAS, Nature Human Behavior, npj Digital Medicine, ACM CSUR, TIPAMI, TKDE, JAMIA, SNAM, etc.
Editorial Board:
Associate Editor, Smart Health
Recognition:
Top Reviewer of NeurIPS 2023.
Page updated
Google Sites
Report abuse