profile picture

Hongyang Zhang

University of Waterloo, Vector Institute for AI

peai: safety

robustness & trustworthiness

snlp: language models

ml: scalability of ml systems

benchmark analysis

text-to-vis

real-world alignment

2

presentations

2

number of views

SHORT BIO

Hongyang Zhang is a tenure-track assistant professor at University of Waterloo and Vector Institute for AI. He received his PhD in 2019 from Machine Learning Department at Carnegie Mellon University and did a Postdoc at Toyota Technological Institute at Chicago. He is the winner of NeurIPS 2018 Adversarial Vision Challenge, CVPR 2021 Security AI Challenger, Amazon Research Award, WAIC Yunfan Award, etc. His paper on adversarial security ranks 13/6729 (top 0.19%) for its citations among all accepted papers in ICML 2018-2023. He also served as an area chair for NeurIPS, ICLR, AISTATS, AAAI, ACM CCS, and an action editor for DMLR.

Presentations

EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Yuhui Li and 3 other authors

New Advances in Safe and Efficient Large Language Models

Hongyang Zhang

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved