News

Research Excellence Award Russia 2021
06 Apr 2021

Dmitry Vetrov was awarded the prestigious Research Excellence Award Russia 2021 in the nomination ‘Contribution to the development of a globally relevant research topic’ for his work on Convolutional Neural Networks.

The Research Excellence Award Russia is presented by Elsevier, the world's largest publisher of scientific and technical literature and provider of information solutions in the field of science and education.

Dmitry Vetrov dedicated the award to his students, past and current.
Two papers were accepted to NAACL 2021
12 Mar 2021
Two papers were accepted to the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021):
- “On the Embeddings of Variables in Recurrent Neural Networks for Source Code” by Nadezhda Chirkova;
- “A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code” by Nadezhda Chirkova and Sergey Troshin.
Samsung Best Paper Award 2020
05 Oct 2020

The paper "Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics" by Arseny Kuznetsov, Pavel Shvechikov, Alexander Grishin, and Dmitry Vetrov earned a bronze award on Samsung Best Paper Award 2020. It is the central academic competition at Samsung which stimulates engineers and researchers to publish world-class level papers. Our members' paper was the only one from Russia that made it to the final stage along with 107 other papers (among 2180 initial submissions) from all over the world.
NeurIPS 2020
28 Sep 2020

The paper On Power Laws in Deep Ensembles by Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan and Dmitry Vetrov has been aceepted to NeurIPS 2020 for a spotlight presentation.
Dmitry Vetrov joins the ELLIS Society
24 Aug 2020

Dmitry Vetrov is the first Russian scientist to be elected as a member to the ELLIS Society (the European Laboratory for Learning and Intelligent Systems), a leading European organization in the field of artificial intelligence.

Being a member of the ELLIS Society, Dmitry Vetrov says, will provide more opportunities for students and doctoral students in the faculty.
ICML 2020
02 Jun 2020
Two papers have been accepted to the conference track of ICML 2020:
- Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics by Arseny Kuznetsov, Pavel Shvechikov, Alexander Grishin, Dmitry Vetrov
- Involutive MCMC: One Way to Derive Them All by Kirill Neklyudov, Dmitry Vetrov in collaboration with Max Welling and Evgenii Egorov
And the paper "On Power Laws in Deep Ensembles" by Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, and Dmitry Vetrov has been accepted to the Workshop on Uncertainty and Robustness in Deep Learning, ICML 2020
UAI 2020
15 May 2020

A paper Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation by Dmitry Molchanov, Alexander Lyzhov, Yuliya Molchanova, Arsenii Ashukha and Dmitry Vetrov has been accepted to the conference track of UAI 2020.
ICLR and AISTATS 2020
16 Apr 2020

A paper Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning by Arsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov and Dmitry Vetrov has been accepted to the conference track of ICLR 2020, and Deterministic Decoding for Discrete Data in Variational Autoencoders by Daniil Polykovskiy and Dmitry Vetrov has been accepted to AISTATS 2020.
Anton Osokin became the winner of the Moscow Government Young Scientist Prize for 2019
16 Jan 2020

The prize was awarded for a cycle of papers on machine learning methods for predicting structured objects. The cycle includes 13 works of 2011-2019 published at leading international conferences such as NeurIPS, ICML, CVPR, ICCV, ICLR and in the leading journals IEEE TPAMI and IJCV.
AAAI 2020
11 Dec 2019
Two papers have been accepted to the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020):
- Structured Sparsification of Gated Recurrent Neural Networks by Ekaterina Lobacheva, Nadezhda Chirkova, Aleksandr Markovich, and Dmitry Vetrov
- Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution by Artyom Gadetsky, Kirill Struminsky, Dmitry Vetrov in collaboration with Christopher Robinson and Novi Quadrianto.

← Newer Page 2 out of 4 Older →