Hi! I'm Yuan Yin

Postdoctoral AI Researcher at Valeo.ai. PhD from the MLIA Team at Sorbonne Université, ISIR.

yuan-yin.jpeg

That's me at Københavns Rådhus in 2022.

My research focuses on machine learning and deep learning for (spatio)temporal sequence modeling, prediction, and analysis of complex behaviors.

I have explored the following directions in the past few years, with a special emphasis on physical dynamical systems:

  • physics dynamics modeling with neural networks,
  • adaptation and out-of-distribution generalization of neural networks, and
  • handling free-form data and predicting phenomena continuously in time and space.

I successfully defended my PhD thesis in June 2023 at Sorbonne Université, supervised by Prof. Patrick Gallinari and Assoc. Prof. Nicolas Baskiotis.

Prior to that, I earned my BSc in Computer Science from Beihang University back in 2016, followed by an MSc in Computer Science from Université Paris Cité (M1 MPRI) and Sorbonne Université (M2 DAC) in 2019.

News More >>>

2024-09-25 📚 GEPS, a paper I co-authored, has been accepted to NeurIPS 2024!
2024-08-11 📚 Our latest work, ReGentS, has been accepted to ECCV 2024 W-CODA workshop!
2024-04-19 🏅 I received the Accessit ex-aequo for the AFIA 2024 AI Thesis Prize.
2024-04-07 📚 TimeFlow, a paper I co-ordinated, has been accepted to TMLR!
2024-04-02 🌱 I started as a Postdoctoral AI Researcher at Valeo.ai.
2024-03-03 📚 2 papers I co-authored have been accepted to ICLR 2024 AI4DiffEqtnsInSci Workshop!
2024-01-31 🎙️ I gave a talk at the Workshop “Mathematical Foundations of AI”, at DATAIA-SCAI
2024-01-25 🎙️ I gave a talk at the seminar at Valeo.ai.
2023-12-13 🏅 I have been recognized as a Top Reviewer at NeurIPS 2023!
2023-11-30 🎙️ I gave a talk at the seminar of UMR MIA Paris-Saclay, at AgroParisTech.
2023-11-20 🎙️ I gave a talk on APHYNITY at the seminar of Team MCS of Laboratoire Analyse, Géométrie et Applications, at Université Sorbonne Paris Nord (Paris-13).
2023-09-22 🎙️ Patrick and I co-presented at ECML-PKDD 2023 the tutorial on Physics-Aware Deep Learning (Site & slides)
2023-09-21 📚 CORAL, a paper I co-ordinated, has been accepted at NeurIPS 2023!
2023-06-28 🎓 I successfully defended my PhD thesis.
2023-06-19 📚 INFINITY, a paper I co-ordinated, has been accepted at ICML 2023 Workshop on SynS&ML!
2023-05-04 🎙️ I presented CoDA and DINo at the Seminar of Signal Processing Laboratory (LTS4) at EPFL
2023-05-03 I’m sorry to announce that I won’t be able to attend our ICLR spotlight presentation of DINo in Kigali, Rwanda. Please check our paper, poster and slides here.
2023-04-17 🎙️ Matthieu and I gave a talk on DINo at AI for Science Talks.
2023-03-27 🎙️ I gave a talk on APHINITY at the seminar of SIG LearnSFluid.
2023-03-20 🎙️ I was invited to give a talk at AP-HP on applying machine learning to medical biology.
2023-01-21 📚 Our latest work, DINo, has been accepted at ICLR 2023 as a Spotlight paper (officially called Notable-Top-25%).
2022-11-28 🎙️ Jean-Yves and I gave a talk on DINo at the seminar of Criteo AI Lab.
2022-10-18 🎙️ I presented APHYNITY at the joint seminar of Sorbonne Université, ISAE, and Cerfacs.
2022-07-17 🎙️ Matthieu presented our work CoDA in person at ICML 2022 in New Orleans.
2022-05-14 📚 Our work, CoDA, has been accepted at ICML 2022 as Spotlight presentation.
2022-02-08 🎙️ I gave a talk on my work on hybrid modeling and generalization at Extrality, a French startup working on machine learning accelerated CFD models.
2021-12-08 🎙️ I presented our work LEADS at NeurIPS 2021 and NeurIPS@Paris 2021.
2021-09-27 📚 Our work, LEADS, has been accepted at NeurIPS 2021.
2021-05-06 🎙️ Ibrahim presented APHYNITY at ICLR 2021.
2021-03-22 🎙️ I presented the short version of LEADS at AAAI 2021 MLPS Spring Symposium.
2021-02-20 📚 The short version of LEADS has been accepted to AAAI 2021 MLPS Spring Symposium.
2021-01-07 📚 Our work, APHYNITY, has been accepted at ICLR 2021 as Oral presentation.
2019-10-04 🎙️ I presented “Unsupervised Inpainting for Occluded Sea Surface Temperature Sequences” at CI 2019.
2019-10-01 🌱 I started as PhD Student in the MLIA team at Sorbonne Université.
2019-08-09 🎙️ Our work, Unsupervised Inpainting for Occluded Sea Surface Temperature Sequences, has been accepted to CI 2019.
2019-02-18 🌱 I started my intership in the MLIA team at Sorbonne Université.