Adrien Petralia

PhD, Applied AI Scientist
@ Mistral

Contact Me Learn More
Adrien Petralia
Paris, France
Google Scholar LinkedIn GitHub ResearchGate ORCID

About Me

I am currently an Applied AI Scientist at Mistral AI. I completed my Ph.D. in Artificial Intelligence at Université Paris Cité, under the supervision of Prof. Themis Palpanas. My thesis, Deep Learning for Electricity Consumption Time Series Analytics, introduced novel scalable deep-learning methods for extracting information from very low-frequency smart-meter data.

Research Interests

Data Mining Time Series Deep Learning Pattern Recognition Non-Intrusive Load Monitoring

News

  1. Release TS-ICL Time Series Foundation Models

    We released TS-ICL, a time-indexed foundation model for zero-shot time-series forecasting and imputation. The paper is now available on arXiv, together with the open-source code.

  2. Award INFORSID

    I received the 2026 INFORSID PhD Thesis Award for my PhD thesis on deep learning for electricity consumption time-series analytics.

  3. Award Think Smartgrids

    I received the Think Smartgrids Thesis Award for my PhD work on deep learning for electricity consumption time-series analytics.

  4. Conference NeurIPS San Diego, CA, USA

    I attended NeurIPS 2025 in San Diego and presented a paper at the BERT2TS workshop on Recent Advances in Time Series Foundation Models.

  5. Conference KDD Toronto, ON, Canada

    I attended the KDD 2025 conference and presented the last paper from my PhD thesis.

  6. Conference ICDE Hong Kong SAR, China

    I attended and presented two papers at ICDE 2025 in Hong Kong.

  7. PhD Defense Université Paris Cité Paris, France

    I successfully defended my PhD at Université Paris Cité !

  8. Conference VLDB Guangzhou, China

    I attended and presented two papers at the VLDB 2024 conference in Guangzhou.

  9. Science Outreach Double•Science Paris, France

    As part of the UP Cité delegation , I presented an accessible overview of my research work during a session titled "How can AI helps us understand electricity consumption?" at the Double•Science outreach festival in Paris.

Publications

Research publications and academic work.

Thesis

PhD thesis summary.

Teaching and Service

Teaching, supervision, program committees, and peer review.