Andrew Williams
Visiting Researcher
AI Research Partnerships & Ecosystem
Andrew Robert Williams is a Visiting Researcher at ServiceNow Research in the Human Decision Support Program. He is also a machine Learning PhD student at Mila - Quebec AI Institute in the CERC-AAI lab. He holds an M. Sc. in Computer Science for Université de Montréal, where we was advised by Alain Tapp and Gilles Brassard. Andrew’s research interests include complex systems modelling, agentic AI, multimodality and time series forecasting.
Intérêts
- Time Series Forecasting
- Multimodal Models
Publications
Dr-CiK: A Testbed for Foresight-Driven Agents.
Workshop at the International Conference of Machine Learning (ICML),
2026.
Overcoming the Modality Gap in Context-Aided Forecasting.
International Conference on Machine Learning (ICML),
2026.
Overcoming the Modality Gap in Context-Aided Forecasting.
Workshop at the International Conference of Machine Learning (ICML),
2026.
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs.
Workshop at the Neural Information Processing Systems (NeurIPS),
2025.
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs.
Conference on Language Modeling Workshops,
2025.
Context is Key: A Benchmark for Forecasting with Essential Textual Information.
International Conference on Machine Learning (ICML),
2025.
Context is Key: A Benchmark for Forecasting with Essential Textual Information.
Workshop at the Neural Information Processing Systems (NeurIPS),
2024.
Context is Key: A Benchmark for Forecasting with Essential Textual Information.
Foundation Models for Time Series,
2024.
Context is Key: A Benchmark for Forecasting with Essential Textual Information.
Montreal AI Symposium (MAIS),
2024.
Lag-Llama: A Foundation Model for Probabilistic Time Series Forecasting.
Workshop at the Neural Information Processing Systems (NeurIPS),
2023.