Xiangyu Zhou

According to our database, Xiangyu Zhou authored at least 11 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation.

Rafi Ibn Sultan, Hui Zhu, Xiangyu Zhou, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu

CoRR, March, 2026

Attention Smoothing Is All You Need For Unlearning.

Saleh Zare Zade, Xiangyu Zhou, Sijia Liu, Dongxiao Zhu

CoRR, March, 2026

Not All Tokens Are Meant to Be Forgotten.

Xiangyu Zhou, Yao Qiang, Saleh Zare Zade, Douglas Zytko, Prashant Khanduri, Dongxiao Zhu

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Trauma-Informed Data Donation: Integrating Expert and Donor Perspectives on Designing Against Re-Traumatization During Collection of Sexual Violence Data.

Emma Walquist, Wenqi Zheng, Isha Datey, Xiangyu Zhou, Kelly Berishaj, Melissa Mcdonald, Michele Parkhill, Dongxiao Zhu, Douglas Zytko

Proceedings of the 2026 Designing Interactive Systems Conference, 2026

2025

Collective Consent: Who Needs to Consent to the Donation of Data Representing Multiple People?

Emma Walquist, Isha Datey, Wenqi Zheng, Xiangyu Zhou, Kelly Berishaj, Melissa Mcdonald, Michele Parkhill, Dongxiao Zhu, Douglas Zytko

Proc. ACM Hum. Comput. Interact., 2025

Automatic Calibration for Membership Inference Attack on Large Language Models.

Saleh Zare Zade, Yao Qiang, Xiangyu Zhou, Hui Zhu, Mohammad Amin Roshani, Prashant Khanduri, Dongxiao Zhu

Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

2024

Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19.

Mohammad Amin Roshani, Xiangyu Zhou, Yao Qiang, Srinivasan Suresh, Steve Hicks, Usha Sethuraman, Dongxiao Zhu

CoRR, 2024

Learning to Poison Large Language Models During Instruction Tuning.

Yao Qiang, Xiangyu Zhou, Saleh Zare Zade, Mohammad Amin Roshani, Douglas Zytko, Dongxiao Zhu

CoRR, 2024

"It's Not What We Were Trying to Get At, but I Think Maybe It Should Be": Learning How to Do Trauma-Informed Design with a Data Donation Platform for Online Dating Sexual Violence.

Wenqi Zheng, Emma Walquist, Isha Datey, Xiangyu Zhou, Kelly Berishaj, Melissa Mcdonald, Michele Parkhill, Dongxiao Zhu, Douglas Zytko

Proceedings of the CHI Conference on Human Factors in Computing Systems, 2024

2023

Hijacking Large Language Models via Adversarial In-Context Learning.

Yao Qiang, Xiangyu Zhou, Dongxiao Zhu

CoRR, 2023

Towards Trauma-Informed Data Donation of Sexual Experience in Online Dating to Improve Sexual Risk Detection AI.

Wenqi Zheng, Emma Walquist, Isha Datey, Xiangyu Zhou, Kelly Berishaj, Melissa Mcdonald, Michele Parkhill, Dongxiao Zhu, Douglas Zytko

Proceedings of the Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 2023