surfing gradients // drunk on apophenia

Gia Khanh Nguyen

Product at insightfactory.ai, building agentic AI.

Research at the Australian Institute for Machine Learning with Prof. Minh Hoai Nguyen's BBVisual Lab, on vision–language models and visual reasoning.

Adelaide, South Australia.

github · linkedin · x · youtube · substack · rss

Publications

• CountEx: Fine-Grained Counting via Exemplars and Exclusion. Yifeng Huang, Gia Khanh Nguyen, Minh Hoai. ECCV, 2026. [paper] [code]
• Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation. Gia Khanh Nguyen, Yifeng Huang, Minh Hoai. DICTA, 2025. [paper] [code]

Writing

• 
  If It's Meant to Be, It Will Be

  27 August, 2024 · A reflection on embracing uncertainty and finding peace in letting go.
• 
  The Future of AI Backdoor Attacks

  2 July, 2024 · A bit of thoughts about backdoor attacks and its future
• 
  The Weight of Knowing

  18 June, 2024 · Sometimes, protecting your peace is okay.
• 
  Failure is not one of the options

  31 May, 2024 · A reflection on my own experiences with triumphs and defeats.
• 
  My parents' language

  2 April, 2024 · This was written on my birthday.

All writing, also on Substack.