Scholar
Nicolas Gontier
Google Scholar ID: KNaO2qUAAAAJ
ServiceNow Research
Citations & Impact
Citations
2,138
H-index
6
i10-index
4
Publications
18
Co-authors
32
list available
Publications
Resume (English only)
Academic Achievements
- Published papers including 'How to Train Your LLM Web Agent: A Statistical Diagnosis', 'Self-Evolving Curriculum for LLM Reasoning', 'Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning', 'TapeAgents: a Holistic Framework for Agent Development and Optimization', PhD Thesis 'Natural Language Reasoning with Transformer Language Models', and several other academic articles.
Research Experience
- Currently a Research Scientist at ServiceNow Research; Organized the REALM workshop; Served as Reviewer, Action Editor, Advisor, and Teaching Assistant.
Education
- Obtained a Bachelor of Science (B.Sc.) in Computer Science from McGill University in 2016 with a minor in Economics; Master of Science (M.Sc.) in Computer Science from McGill University in 2018, supervised by Professor Joelle Pineau, focusing on dialogue systems; Ph.D. from Polytechnique Montreal in May 2023, supervised by Professor Christopher Pal, focusing on proof generation and multi-step reasoning with Transformer Language Models.
Background
- Research interests lie at the intersection of Natural Language Processing (NLP) and Reasoning, particularly in Large Language Models (LLMs) that use external tools and language generation systems such as conversational agents. Also curious about a broad range of other topics including Finance, AI Security, theoretical physics, AI in medicine, neuroscience, and anything related to multimedia (3D animations, movie making, music).
Miscellany
- Interests include finance, AI security, theoretical physics, AI in medicine, neuroscience, and multimedia (3D animations, movie making, music).
