Valentin Liévin (profile picture)

Valentin Liévin

ML research @ Google DeepMind

Better LLMs for healthcare and science.

I focus on enhancing retrieval and reasoning to advance the AI frontier in healthcare and science.

I completed my PhD at the Technical University of Denmark (DTU), during which I focused on variational inference, generative models, optimization and retrieval for health applications. I submitted my PhD thesis Deep Latent Variable Models for Natural Language Processing in October 2022.

Publications

Towards Conversational AI for Disease Management
Anil Palepu, Valentin Liévin, Wei-Hung Weng, Khaled Saab, David Stutz, Yong Cheng, Kavita Kulkarni, S. Sara Mahdavi, Joëlle Barral, Dale R. Webster, Katherine Chou, Avinatan Hassidim, Yossi Matias, James Manyika, Ryutaro Tanno, Vivek Natarajan, Adam Rodman, Tao Tu, Alan Karthikesalingam, Mike Schaekermann
Arxiv Preprint, 2025
Deep Latent Variable Models for Natural Language Processing
Valentin Liévin
PhD thesis, Technical University of Denmark
ThoughtSource: A central hub for large language model reasoning data
Simon Ott, Konstantin Hebenstreit, Valentin Liévin, Christoffer Egeberg Hother, Milad Moradi, Maximilian Mayrhauser, Robert Praas, Ole Winther, Matthias Samwald
Scientific Data, 2023
Variational Open-Domain Question Answering
Valentin Liévin, Andreas Geert Motzfeldt, Ida Riis Jensen, Ole Winther
International Conference on Machine Learning (ICML), 2023
Can large language models reason about medical questions?
Valentin Liévin, Christoffer Egeberg Hother, Ole Winther
Patterns, 2022
FindZebra online search delving into rare disease case reports using natural language processing
Valentin Liévin, Jonas Meinertz Hansen, Allan Lund, Deborah Elstein, Mads Emil Matthiesen, Kaisa Elomaa, Kaja Zarakowska, Iris Himmelhan, Jaco Botha, Hanne Borgeskov, Ole Winther
PLOS Digital Health, 2023
Image Super-Resolution With Deep Variational Autoencoders
Darius Chira, Ilian Haralampiev, Ole Winther, Andrea Dittadi, Valentin Liévin
Advances in Image Manipulation workshop and challenges (ECCV), 2022
Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
Valentin Liévin, Andrea Dittadi, Anders Christensen, Ole Winther
Neural Information Processing Systems (NeurIPS), 2020
BIVA: A very deep hierarchy of latent variables for generative modeling
Lars Maaløe, Marco Fraccaro, Valentin Liévin and Ole Winther
Neural Information Processing Systems (NeurIPS), 2019
Towards Hierarchical Discrete Variational Autoencoders
Valentin Liévin, Andrea Dittadi, Lars Maaløe and Ole Winther
Second Symposium on Advances in Approximate Bayesian Inference, 2019