Andrey Zhmoginov

38 papers A* 8Journal 26Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Contextually Guided Transformers via Low-Rank Adaptation. CoRR Andrey Zhmoginov, Jihwan Lee, Max Vladymyrov, Mark Sandler
2025	A*	`conf`	How new data permeates LLM knowledge and how to dilute it. ICLR Chen Sun, Renat Aksitov, Andrey Zhmoginov, Nolan Andrew Miller, Max Vladymyrov, Ulrich Rueckert, Been Kim, Mark Sandler
2025	J	`jnl`	How new data permeates LLM knowledge and how to dilute it. CoRR Chen Sun, Renat Aksitov, Andrey Zhmoginov, Nolan Andrew Miller, Max Vladymyrov, Ulrich Rueckert, Been Kim, Mark Sandler
2025	J	`jnl`	Long Context In-Context Compression by Getting to the Gist of Gisting. CoRR Aleksandar Petrov, Mark Sandler, Andrey Zhmoginov, Nolan Miller, Max Vladymyrov
2025	A*	`conf`	MELODI: Exploring Memory Compression for Long Contexts. ICLR Yinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov, David Racz, Jesper Sparre Andersen
2025	J	`jnl`	Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones. CoRR Andrey Zhmoginov, Jihwan Lee, Mark Sandler
2024	J	`jnl`	Continual HyperTransformer: A Meta-Learner for Continual Few-Shot Learning. Trans. Mach. Learn. Res. Max Vladymyrov, Andrey Zhmoginov, Mark Sandler
2024	J	`jnl`	Learning and Unlearning of Fabricated Knowledge in Language Models. CoRR Chen Sun, Nolan Andrew Miller, Andrey Zhmoginov, Max Vladymyrov, Mark Sandler
2024	J	`jnl`	MELODI: Exploring Memory Compression for Long Contexts. CoRR Yinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov, David Racz, Jesper Sparre Andersen
2024	J	`jnl`	Narrowing the Focus: Learned Optimizers for Pretrained Models. CoRR Gus Kristiansen, Mark Sandler, Andrey Zhmoginov, Nolan Miller, Anirudh Goyal, Jihwan Lee, Max Vladymyrov
2023	J	`jnl`	Continual Few-Shot Learning Using HyperTransformers. CoRR Max Vladymyrov, Andrey Zhmoginov, Mark Sandler
2023	A*	`conf`	Decentralized Learning with Multi-Headed Distillation. CVPR Andrey Zhmoginov, Mark Sandler, Nolan Miller, Gus Kristiansen, Max Vladymyrov
2023	J	`jnl`	Training trajectories, mini-batch losses and the curious role of the learning rate. CoRR Mark Sandler, Andrey Zhmoginov, Max Vladymyrov, Nolan Miller
2023	A*	`conf`	Transformers Learn In-Context by Gradient Descent. ICML Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo, João Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, Max Vladymyrov
2022	J	`jnl`	Decentralized Learning with Multi-Headed Distillation. CoRR Andrey Zhmoginov, Mark Sandler, Nolan Miller, Gus Kristiansen, Max Vladymyrov
2022	A*	`conf`	Fine-tuning Image Transformers using Learnable Memory. CVPR Mark Sandler, Andrey Zhmoginov, Max Vladymyrov, Andrew Jackson
2022	J	`jnl`	Fine-tuning Image Transformers using Learnable Memory. CoRR Mark Sandler, Andrey Zhmoginov, Max Vladymyrov, Andrew Jackson
2022	A*	`conf`	HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning. ICML Andrey Zhmoginov, Mark Sandler, Maksym Vladymyrov
2022	J	`jnl`	HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning. CoRR Andrey Zhmoginov, Mark Sandler, Max Vladymyrov
2022	J	`jnl`	Transformers learn in-context by gradient descent. CoRR Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo, João Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, Max Vladymyrov
2021	—	`conf`	BasisNet: Two-Stage Model Synthesis for Efficient Inference. CVPR Workshops Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka
2021	J	`jnl`	BasisNet: Two-stage Model Synthesis for Efficient Inference. CoRR Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew G. Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka
2021	J	`jnl`	Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks. CoRR Andrey Zhmoginov, Dina Bashkirova, Mark Sandler
2021	A*	`conf`	Meta-Learning Bidirectional Update Rules. ICML Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Tom Madams, Andrew Jackson, Blaise Agüera y Arcas
2021	J	`jnl`	Meta-Learning Bidirectional Update Rules. CoRR Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Andrew Jackson, Tom Madams, Blaise Agüera y Arcas
2020	J	`jnl`	Image segmentation via Cellular Automata. CoRR Mark Sandler, Andrey Zhmoginov, Liangcheng Luo, Alexander Mordvintsev, Ettore Randazzo, Blaise Agüera y Arcas
2020	—	`conf`	Information-Bottleneck Approach to Salient Region Discovery. ECML/PKDD (3) Andrey Zhmoginov, Ian Fischer, Mark Sandler
2020	J	`jnl`	Large-Scale Generative Data-Free Distillation. CoRR Liangchen Luo, Mark Sandler, Zi Lin, Andrey Zhmoginov, Andrew Howard
2019	J	`jnl`	Information-Bottleneck Approach to Salient Region Discovery. CoRR Andrey Zhmoginov, Ian Fischer, Mark Sandler
2019	—	`conf`	K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning. ICLR (Poster) Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew G. Howard
2019	—	`conf`	Non-Discriminative Data or Weak Model? On the Relative Importance of Data and Model Resolution. ICCV Workshops Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard
2019	J	`jnl`	Non-discriminative data or weak model? On the relative importance of data and model resolution. CoRR Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard
2018	J	`jnl`	Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen
2018	J	`jnl`	K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning. CoRR Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew G. Howard
2018	A*	`conf`	MobileNetV2: Inverted Residuals and Linear Bottlenecks. CVPR Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen
2017	J	`jnl`	CycleGAN, a Master of Steganography. CoRR Casey Chu, Andrey Zhmoginov, Mark Sandler
2017	J	`jnl`	The Power of Sparsity in Convolutional Neural Networks. CoRR Soravit Changpinyo, Mark Sandler, Andrey Zhmoginov
2016	J	`jnl`	Inverting face embeddings with convolutional neural networks. CoRR Andrey Zhmoginov, Mark Sandler