AZ

Andrey Zhmoginov

cs.LGcs.CVcs.AIcs.CLphysics.plasm-phcs.NEmath.MPmath-phstat.MLcs.IT

On Valency

published · living versions

MobileNetV2: Inverted Residuals and Linear Bottlenecks

with Mark Sandler, Andrew Howard, Menglong Zhu, Liang-Chieh Chen

1 version

W_32x3r2a2v1 · current

Preprints & journals

36 papers in the corpus · 2010–2026

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

Hoang Phan, Dat Huynh, Andrey Zhmoginov et al.

0 citations

2610.09484v22026arXiv

LoRA-generating hypernetworks for efficient on-device LLM generative personalization

Sean Augenstein, Li Ding, Jihwan Lee et al.

0 citations

2609.24979v12026arXiv

Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones

Andrey Zhmoginov, Jihwan Lee, Mark Sandler

0 citations

2506.05641v12025arXiv

Contextually Guided Transformers via Low-Rank Adaptation

Andrey Zhmoginov, Jihwan Lee, Max Vladymyrov et al.

0 citations

2506.05672v12025arXiv

How new data permeates LLM knowledge and how to dilute it

Chen Sun, Renat Aksitov, Andrey Zhmoginov et al.

1 citation

2504.09522v12025arXiv

Long Context In-Context Compression by Getting to the Gist of Gisting

Aleksandar Petrov, Mark Sandler, Andrey Zhmoginov et al.

0 citations

2504.08934v12025arXiv

Learning and Unlearning of Fabricated Knowledge in Language Models

Chen Sun, Nolan Andrew Miller, Andrey Zhmoginov et al.

0 citations

2410.21750v12024ICML 2024 Workshop on Mechanistic Interpretability

MELODI: Exploring Memory Compression for Long Contexts

Yinpeng Chen, DeLesley Hutchins, Aren Jansen et al.

1 citation

2410.03156v12024arXiv

Narrowing the Focus: Learned Optimizers for Pretrained Models

Gus Kristiansen, Mark Sandler, Andrey Zhmoginov et al.

0 citations

2408.09310v32024arXiv

Continual HyperTransformer: A Meta-Learner for Continual Few-Shot Learning

Max Vladymyrov, Andrey Zhmoginov, Mark Sandler

3 citations

2301.04584v32023arXiv

Training trajectories, mini-batch losses and the curious role of the learning rate

Mark Sandler, Andrey Zhmoginov, Max Vladymyrov et al.

1 citation

2301.02312v22023arXiv

Transformers learn in-context by gradient descent

Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo et al.

87 citations

2212.07677v22022arXiv

Decentralized Learning with Multi-Headed Distillation

Andrey Zhmoginov, Mark Sandler, Nolan Miller et al.

8 citations

2211.15774v12022arXiv

Fine-tuning Image Transformers using Learnable Memory

Mark Sandler, Andrey Zhmoginov, Max Vladymyrov et al.

55 citations

2203.15243v22022arXiv

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning

Andrey Zhmoginov, Mark Sandler, Max Vladymyrov

29 citations

2201.04182v32022arXiv

Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks

Andrey Zhmoginov, Dina Bashkirova, Mark Sandler

3 citations

2107.10963v12021arXiv

BasisNet: Two-stage Model Synthesis for Efficient Inference

Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov et al.

6 citations

2105.03014v12021arXiv

Meta-Learning Bidirectional Update Rules

Mark Sandler, Max Vladymyrov, Andrey Zhmoginov et al.

5 citations

2104.04657v22021arXiv

Large-Scale Generative Data-Free Distillation

Liangchen Luo, Mark Sandler, Zi Lin et al.

29 citations

2012.05578v12020arXiv

Image segmentation via Cellular Automata

Mark Sandler, Andrey Zhmoginov, Liangcheng Luo et al.

8 citations

2008.04965v22020arXiv

Non-discriminative data or weak model? On the relative importance of data and model resolution

Mark Sandler, Jonathan Baccash, Andrey Zhmoginov et al.

33 citations

1909.03205v22019arXiv

Information-Bottleneck Approach to Salient Region Discovery

Andrey Zhmoginov, Ian Fischer, Mark Sandler

23 citations

1907.09578v22019arXiv

K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning

Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov et al.

39 citations

1810.10703v22018arXiv

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Mark Sandler, Andrew Howard, Menglong Zhu et al.

28,599 citations

1801.04381v42018The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510-4520

CycleGAN, a Master of Steganography

Casey Chu, Andrey Zhmoginov, Mark Sandler

160 citations

1712.02950v22017arXiv

The Power of Sparsity in Convolutional Neural Networks

Soravit Changpinyo, Mark Sandler, Andrey Zhmoginov

116 citations

1702.06257v12017arXiv

Variational principles for dissipative (sub)systems, with applications to the theory of linear dispersion and geometrical optics

I. Y. Dodin, A. I. Zhmoginov, D. E. Ruiz

16 citations

1610.05668v22016arXiv

Inverting face embeddings with convolutional neural networks

Andrey Zhmoginov, Mark Sandler

54 citations

1606.04189v22016arXiv

An improved limit on the charge of antihydrogen from stochastic acceleration.

Ahmadi, M, Baquero-Ruiz, M, Bertsche, W et al.

61 citations

267917252016Nature. 2016;529(7586):373-6

An experimental limit on the charge of antihydrogen.

Amole, C, Ashkezari, M D, Baquero-Ruiz, M et al.

59 citations

248928002015Nature communications. 2014;5:3955

Antimatter interferometry for gravity measurements.

Hamilton, Paul, Zhmoginov, Andrey, Robicheaux, Francis et al.

71 citations

247246442014Physical review letters. 2014;112(12):121102

Hamiltonian mechanics of stochastic acceleration.

Burby, J W, Zhmoginov, A I, Qin, H

5 citations

242664762014Physical review letters. 2013;111(19):195001

Autoresonant-spectrometric determination of the residual gas composition in the ALPHA experiment apparatus.

Amole, C, Ashkezari, M D, Baquero-Ruiz, M et al.

3 citations

238223812014The Review of scientific instruments. 2013;84(6):065110

Description and first application of a new technique to measure the gravitational mass of antihydrogen.

ALPHA Collaboration, Charman, A E, Amole, C et al.

239 citations

236531972013Nature communications. 2013;4:1785

Channeling of fusion alpha-particle power using minority ion catalysis.

Zhmoginov, A I, Fisch, N J

8 citations

221075282012Physical review letters. 2011;107(17):175001

Negative effective mass of wave-driven classical particles in dielectric media.

Zhmoginov, A I, Dodin, I Y, Fisch, N J

5 citations

203658792010Physical review. E, Statistical, nonlinear, and soft matter physics. 2010;81(3 Pt 2):036404

Career total: 64 works. 36 are in this corpus.

Profile built from the corpus for this byline.

64

works

30.6K

citations

19

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.