ServiceNow Research

Aristides Milios

Aristides Milios

Visiting Researcher

AI Frontier Research

I’m a passionate machine learning researcher and PhD student at Université de Montréal & MILA, specializing in Natural Language Processing and Vision/Text Foundation Models. My research focuses on investigating the real-world reasoning and self-improvement abilities of large language models, especially in the context of language models as agents and tool-use. Previously, I completed my M.Sc. at McGill University under the supervision of Dr. Siva Reddy and Dr. Dzmitry Bahdanau (researching using LLMs in conjunction with dense retrieval models for in-context demonstration selection), and gained industry experience as a Research Intern at ServiceNOW (researching self-evaluation and self-improvement in the context of promoting conciseness when it comes to topics the LLM is likely to hallucinate about). Having started a PhD under Dr. Chris Pal at UdeM in September 2024, my aim is to apply LLMs to real-world use cases, such as interactive and iterative dialogue-based design assistants, as well as continuing to investigate the ability of the models to self-improve though self-evaluation.

My journey in tech began with entrepreneurship, co-founding Bitness.io and participating in accelerator programs in Atlantic Canada. This experience fueled my passion for innovation and education, leading me to co-found Hoist Halifax, organizing workshops for teens interested in technology and entrepreneurship. As a University Innovation Fellow from Stanford and former co-president of the Dalhousie Entrepreneurship Society, I’ve consistently worked to bridge the gap between cutting-edge tech research and practical applications.

Committed to advancing both the field of machine learning and promoting entrepreneurship, I bring a unique blend of technical expertise and innovative thinking to every project. My goal is to contribute to groundbreaking research in AI while fostering the next generation of tech entrepreneurs and thinkers.

Interests
  • Natural Language Processing
  • Large Language Models
  • Reinforcement Learning
  • Large Code Models

Publications

In-Context Learning for Text Classification with Many Labels. Workshop at the Conference on Empirical Methods in Natural Language Processing (EMNLP),  2022.

PDF Cite