Quy-Anh Dang

Quy-Anh Dang

Researcher, Knovel Engineering

I work on AI Safety (red teaming, alignment), Efficient ML (model merging, efficient training), and Speech Processing.

Email / CV / GitHub / Google Scholar / LinkedIn / X

Latest Writing

All posts →
Local MLOps Mastery: Your Complete Guide to Building ML Systems on Your MachineJune 3, 2025
Understanding AUROC: A Mathematical and Practical PerspectiveMay 3, 2025
Bias-Variance Tradeoff in Machine LearningMay 3, 2025

Featured Projects

All projects →
Open-RS: Enhancing Reasoning in Small LLMs with Reinforcement Learning
An open-source project exploring reinforcement learning techniques to boost reasoning capabilities in small large language models.
Homemade Machine Learning: A Hands-On Journey into ML Algorithms
An educational project featuring Jupyter notebooks to implement and understand machine learning algorithms from scratch.

Recent Publications

All publications →
Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR
Multilinguality in the Era of Large Language Models (MeLLM 2026) @ ACL 2026
Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection
Findings of the Association for Computational Linguistics: ACL 2026
RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models
Principled Design for Trustworthy AI: Interpretability, Robustness, and Safety across Modalities @ ICLR 2026