Dr Yanghao Zhang

Where are you from, and what is your background?

I have been coming to the UK since 2018, where I have pursued my MSc in Artificial Intelligence at the University of Southampton. I have also completed my PhD in Computer Science at the Trustworthy ACPS Lab, University of Liverpool.

What do you do in your spare time?

In my spare time, I enjoy playing table tennis, basketball, and MOBA games with friends.

What influenced you to do a PhD?

Working in academia gives me the freedom to explore cutting-edge ideas and stay at the frontier of knowledge. I especially value the opportunities to discuss new concepts with colleagues and be inspired through open and creative conversations. At the same time, I also work as a senior research scientist at Safe Intelligence, which is a spin-out from Imperial.

What are your research interests?

My research interests lie in robust machine learning and safety verification. I work on developing optimisation algorithms and verification techniques that enhance the reliability, safety, and trustworthiness of AI systems, particularly in safety-critical or uncertain environments.

Publications at SAIL

2026

arXiv 2026

Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models

B. Aron, C. Brix, B. Brückner, Y. Zhang, P. Kouvaros, A. Lomuscio

arXiv
BibTeX
@article{DBLP:journals/corr/abs-2609-22293,
  author     = {Bogdan Aron and Christopher Brix and Benedikt Brückner and Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
  title      = {{Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models}},
  journal    = {CoRR},
  volume     = {abs/2609.22293},
  year       = {2026},
  eprinttype = {arXiv},
  eprint     = {2609.22293},
  doi        = {10.48550/ARXIV.2609.22293}
}
ECCV 2026

IoUCert: Robustness Verification for Anchor-Based Object Detectors

B. Brückner*, A. J. Mercado*, Y. Zhang, P. Kouvaros, A. Lomuscio* Equal contribution

arXivDOI
BibTeX
@inproceedings{DBLP:conf/eccv/BrucknerMZKL26,
  author     = {Benedikt Brückner and Alejandro J. Mercado and Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
  title      = {{IoUCert: Robustness Verification for Anchor-Based Object Detectors}},
  booktitle  = {Computer Vision - ECCV 2026 - 19th European Conference, Malmö, Sweden, September 8-12, 2026, Proceedings, Part XXI},
  series     = {Lecture Notes in Computer Science},
  volume     = {17021},
  pages      = {364--384},
  publisher  = {Springer},
  year       = {2026},
  doi        = {10.1007/978-3-032-37574-2_20}
}

2025

NeurIPS 2025

Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation

Y. Zhang, P. Kouvaros, A. Lomuscio

PDFPublisher
BibTeX
@inproceedings{DBLP:conf/nips/ZhangKL25,
  author     = {Yanghao Zhang and Panagiotis Kouvaros and Alessio Lomuscio},
  title      = {{Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation}},
  booktitle  = {Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diego, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025},
  year       = {2025},
  url        = {http://papers.nips.cc/paper_files/paper/2025/hash/1435ac9924d7621e44aa2407a1cfdec7-Abstract-Conference.html}
}
← All people