About me

I am a Ph.D. student in AI at HKUST (Guangzhou), advised by Prof. Jun Wang, with a background in statistics and machine learning from Warwick and UCL. I work at the interface of AI and industry, with a focus on materials and manufacturing.

Education

• Ph.D. in Artificial Intelligence, HKUST (Guangzhou), 2024 - Present
• M.Sc. in Machine Learning, University College London (UCL), 2022 - 2023
• B.Sc. in Mathematics and Statistics, University of Warwick, 2019 - 2022

Focus

My focus is on bringing AI into industry—especially materials and manufacturing. I’m drawn to settings where information is genuinely expensive and decisions carry real cost: where an experiment takes days, a measurement is limited or destructive, and a single process choice separates yield from scrap. These are the places where a model has to earn its keep, and where getting the decision right actually moves the outcome.

Concretely, I work on process optimization and modeling for manufacturing—predicting film thickness and uniformity, deciding which experiments and measurements are worth running, and controlling processes under uncertainty—together with model-based, open-ended search for materials and molecular discovery. What matters to me is deployment: methods that hold up on real, messy, limited data, run within real constraints, and ship rather than just win on a benchmark.

Recruiting. I’m currently looking for students and interns to work on industrial AI for materials and manufacturing, and I’m open to industry collaboration. If this sounds like your kind of problem, DM me via email.

Keywords: materials & manufacturing · process optimization · industrial AI · experimental design · scientific discovery · decision-making under uncertainty

Publications

• Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search [Code]
  Z. Yu, Y. Song, X. Yan, A. Liu, X. Lu, Y. Chen, et al., J. Wang
  arXiv preprint

• ToolGate: Reducing Perceptual Tool Calls in Vision-Language Agents with Pre-Call Gating [Code]
  A. Liu, Y. Song, Z. Chen, Z. Gong, Z. Yu, J. Wang
  EMNLP 2026

• The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design [Code] [Slides]
  A. Liu*, Z. Gong*, Y. Song, Y. Chen, X. Liu, H. Lu, K. Zhang, C. Wei, J. Wang
  ICML 2026

• Memento-Skills: Let Agents Design Agents
  H. Zhou, S. Guo, A. Liu, Z. Yu, Z. Gong, B. Zhao, et al., J. Wang
  arXiv preprint

• A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning [Code]
  A. Liu*, J. Wang*, S. Kaski, J. Wang, M. Yang
  NeurIPS 2025

• Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
  X. Yu, Z. Wang, L. Yang, H. Li, A. Liu, X. Xue, J. Wang, M. Yang
  NeurIPS 2025

• OpenR: An open source framework for advanced reasoning with large language models [Code]
  J. Wang, M. Fang, Z. Wan, M. Wen, J. Zhu, A. Liu, Z. Gong, Y. Song, L. Chen, et al.
  arXiv preprint

• Attaining Human’s Desirable Outcomes in Human-AI Interaction via Structural Causal Games
  A. Liu, J. Wang, H. Li, X. Chen, J. Wang, S. Kaski, M. Yang
  ICML 2024 Workshop on Humans-Algs-Society

* Equal contribution