Scholar
Andrea Santilli
Google Scholar ID: j2Y_XBIAAAAJ
NLP Researcher
Citations & Impact
Citations
7,047
H-index
11
i10-index
12
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Publications include 'Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces' (CVPR 2025), 'Accelerating Transformer Inference for Translation via Parallel Decoding' (ACL 2023), 'Multimodal Neural Databases' (SIGIR 2023), and more.
Research Experience
- Currently a Research Scientist at Nous Research, conducting post-training research on LLMs with a focus on enhancing their robustness, reliability, and alignment. Formerly an MLR Research Scientist at Apple, working on the robustness and reliability of foundation models via uncertainty estimation. Open Science Researcher at Hugging Face - BigScience, involved in the workshop on large language models, introducing the now popular instruction-tuning training paradigm. Research Engineer at Pi School, School of Artificial Intelligence, working on a European Commission project to promote entrepreneurship and tech transfer in the R&D area via NLP-based tools.
Education
- PhD in Computer Science, 2024, Sapienza University of Rome; MSc in Computer Science, 2020, University of Roma Tor Vergata; BSc in Computer Science, 2018, University of Roma Tor Vergata.
Background
- Research interests include Large Language Models, Natural Language Processing, and Representation Learning. During his PhD, he focused on building effective, efficient, and reliable Large Language Models. He was a Research Scientist Intern at Apple, working with the MLR team. His current research focuses on improving the robustness and reliability of language models through uncertainty estimation and mechanistic interpretability.
Miscellany
- No personal interests mentioned.
