Vincent Michalski

Computer Science · Physical Sciences

15h-index3.1kcitations32works0.42yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(10), Human Pose and Action Recognition(7), Advanced Vision and Imaging(4), Advanced Image and Video Retrieval Techniques(4), Emotion and Mood Recognition(4)

Publications32 total

Neural architectures for visual reasoning
Papyrus : Institutional Repository (Université de Montréal)·2026Open Access
Behaviour Discovery and Attribution for Explainable Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment
arXiv (Cornell University)·2024· 1 citedOpen Access
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
arXiv (Cornell University)·2024Open Access
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
2024· 1 citedOpen Access
Learning Robust Dynamics through Variational Sparse Gating
arXiv (Cornell University)·2022Open Access
Accounting for Variance in Machine Learning Benchmarks
arXiv (Cornell University)·2021· 40 citedOpen Access
Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks
2020· 71 cited
HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
arXiv (Cornell University)·2020· 72 citedOpen Access
HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion
2019· 9 cited
An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
arXiv (Cornell University)·2019· 2 citedOpen Access
An Empirical Study of Batch Normalization and Group Normalization in\n Conditional Computation
arXiv (Cornell University)·2019· 7 citedOpen Access
Towards Deep Conversational Recommendations
PolyPublie (École Polytechnique de Montréal)·2018· 123 citedOpen Access
ChatPainter: Improving Text to Image Generation using Dialogue
arXiv (Cornell University)·2018· 78 citedOpen Access
A Deep Reinforcement Learning Chatbot (Short Version)
arXiv (Cornell University)·2018· 14 citedOpen Access
ChatPainter: Improving Text to Image Generation Using Dialogue
arXiv (Cornell University)·2018· 17 citedOpen Access
FigureQA: An Annotated Figure Dataset for Visual Reasoning
International Conference on Learning Representations·2017· 16 cited
FigureQA: An Annotated Figure Dataset for Visual Reasoning
arXiv (Cornell University)·2017· 122 citedOpen Access
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
2017· 1.4k cited
A Deep Reinforcement Learning Chatbot
arXiv (Cornell University)·2017· 199 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Samira Ebrahimi Kahou(23), Roland Memisevic(13), Yoshua Bengio(12), Kishore Konda(9), Xavier Bouthillier(4), Christopher Pal(4), Dendi Suhubdy(4), Doina Precup(4), Joanna Materzyńska(3), Heuna Kim(3), Valentin Haenel(3), Ingo Fruend(3), P.N. Yianilos(3), Moritz Mueller-Freitag(3), Florian Hoppe(3), Christian Thurau(3), Ingo Bax(3), Pascal Lamblin(3), Çaǧlar Gülçehre(3), Pierre Froumenty(3)