ServiceNow IA recherche

Gabriel Huang

Gabriel Huang

Research Scientist

Adversarial Testing & Risk Evaluation

I am Gabriel (Buo-Xuan) Huang and I recently joined ServiceNow Research as a Research Scientist in the Trustworthiness and AI Governance Lab. I hold a PhD in machine learning from the Montreal Institute for Learning Algorithms (Mila), where I worked under the supervision of Simon Lacoste-Julien.

I am interested in generative learning, latent-variable models, structured prediction, optimal transport, weakly-supervised learning, reinforcement learning, convex optimization, music generation, and fundamental questions of optimization and statistical learning.

Previously I did the MVA Master’s degree in machine learning at École Normale Supérieure in Paris, in parallel with an engineer’s degree at École Centrale Paris (now CentraleSupélec). While I was doing my master’s, I worked for three years in the industry on computer vision and human activity recognition.

Intérêts
  • Trustworthiness
  • Low Supervision
  • Natural Language Processing
  • Large Language Models
  • Dialog
  • Computer Vision
  • Self supervised learning
  • Decission Making
  • Databases
  • Diffusion Models
  • Human Machine Interaction Through Language
  • Text2Structure
  • Multi Step Reasoning
  • Efficient Finetunning of Large Language Models
  • Ethical Reasoning
  • Explainability
  • Security
  • Safety

Publications

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats. Conference on Language Modeling (COLM),  2025.

Article Citation Code

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats. Workshop at the International Conference of Machine Learning (ICML),  2025.

Article Citation Code

TapeAgents: a Holistic Framework for Agent Development and Optimization. ArXiv,  2024.

Article Citation Code Vidéo

A Survey of Self-Supervised and Few-Shot Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI),  2021.

Article Citation Code