Quy-Anh Dang

Quy-Anh Dang

Researcher, Knovel Engineering


Abstract. Researcher with 3+ years of experience developing production-ready AI solutions, specializing in Large Language Models and MLOps systems. Demonstrated research excellence through multiple publications on A* conferences. Strong mathematical foundation combined with hands-on expertise in building end-to-end ML pipelines, retrieval-augmented generation systems, and scalable infrastructure. Focused on advancing research in AI Safety, Efficient Learning, and Speech Processing.

1  Recent News

[2]
Had 1 paper accepted at EMNLP 2026 (Industry Track, Acceptance rate: 28.25%). August 20, 2026.
[3]
Traveled to San Diego, USA to present two accepted papers at ACL 2026. July 2, 2026.
[5]
Became a peer reviewer for NeurIPS 2026, a top-tier ML conference, for the first time. May 7, 2026.

See all news →

2  Recent Publications

[1]
Quy-Anh Dang, Chris Ngo, Truong-Son Hy. RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track. [pdf]
[2]
Quy-Anh Dang, Chris Ngo. Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection. Findings of the Association for Computational Linguistics: ACL 2026. [pdf]
[3]
Quy-Anh Dang, Chris Ngo. Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR. Proceedings of Multilinguality in the Era of Large Language Models @ ACL 2026. [pdf]
[4]
Quy-Anh Dang, Chris Ngo, Truong-Son Hy. 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. [pdf]
[5]
Quy-Anh Dang, Chris Ngo. Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t. Logical and Symbolic Reasoning in Language Models @ AAAI 2026. [pdf]

See all publications →

3  Recent Work

[1]
SeriesLLM Interpretability, Layer by Layer. A beginner-friendly tour of mechanistic interpretability on GPT-2 small, climbing a ladder of evidence: reading the residual stream, probes, sparse autoencoders, activation patching, circuits, steering, and finally a blind audit of a model with a hidden behaviour. 8 parts, updated November 7, 2026.
[2]
SeriesConformal Prediction, Step by Step. A beginner-friendly guide to prediction intervals and sets you can trust: split and full conformal prediction, adaptive intervals, prediction sets for classifiers, distribution shift and time series, and conformal methods for LLMs, with the coverage guarantee checked at every step. 7 parts, updated November 7, 2026.
[3]
SeriesTime Series, Era by Era. A beginner-friendly tour of forecasting, from moving averages and Holt–Winters through ARIMA, machine learning and deep learning to foundation models, all on one dataset, ending with an honest showdown. 8 parts, updated November 5, 2026.
[4]
PostDo Your Annotators Agree? Cohen's Kappa, Krippendorff's Alpha and Friends. Why raw percent agreement misleads, how chance-corrected metrics fix it, when kappa breaks (the prevalence and bias paradoxes), and how to pick an agreement metric for human or LLM-as-a-judge labels. November 4, 2026.
[5]
PostThe Bradley–Terry–Luce Model: Turning Head-to-Head Wins into Scores. How one small formula turns pairwise wins into a ranking: the model, fitting it by maximum likelihood, when it fails to exist, and how it powers Elo, chatbot leaderboards and RLHF reward models. November 3, 2026.

See all work →


© 2026 Quy-Anh Dang. All rights reserved.