English
Related papers

Related papers: DyTox: Transformers for Continual Learning with DY…

200 papers

Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting". Many state-of-the-art solutions to continual learning rely on biasing and/or…

Machine Learning · Computer Science 2020-11-11 Amanda Rios , Laurent Itti

Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale. Their quadratic memory and time complexity, however,…

Computation and Language · Computer Science 2025-05-30 Ali Behrouz , Zeman Li , Praneeth Kacham , Majid Daliri , Yuan Deng , Peilin Zhong , Meisam Razaviyayn , Vahab Mirrokni

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number…

Machine Learning · Computer Science 2018-11-14 Louis Kirsch , Julius Kunze , David Barber

In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting.…

Neural and Evolutionary Computing · Computer Science 2017-11-29 Guglielmo Montone , J. Kevin O'Regan , Alexander V. Terekhov

Complex object manipulation tasks often span over long sequences of operations. Task planning over long-time horizons is a challenging and open problem in robotics, and its complexity grows exponentially with an increasing number of…

Robotics · Computer Science 2020-10-27 Sören Pirk , Karol Hausman , Alexander Toshev , Mohi Khansari

Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with…

Machine Learning · Computer Science 2024-09-17 Joseph Clinton , Robert Lieck

As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a continual learning perspective, in which we aim to continue…

Computation and Language · Computer Science 2023-07-13 Adam Fisch , Amal Rannen-Triki , Razvan Pascanu , Jörg Bornschein , Angeliki Lazaridou , Elena Gribovskaya , Marc'Aurelio Ranzato

Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Junhyeong Cho , Kim Youwang , Tae-Hyun Oh

Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired…

Machine Learning · Computer Science 2023-05-30 Qitian Wu , Chenxiao Yang , Wentao Zhao , Yixuan He , David Wipf , Junchi Yan

Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer$^{-1}$ architecture based on the principle of deep adaptivity. This architecture achieves…

Machine Learning · Computer Science 2025-01-29 Lumen AI , Tengzhou No. 1 Middle School , Shihao Ji , Zihui Song , Fucheng Zhong , Jisen Jia , Zhaobo Wu , Zheyi Cao , Xu Tianhao

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Alexey Buzovkin , Evgeny Shilov

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Quan Tang , Bowen Zhang , Jiajun Liu , Fagui Liu , Yifan Liu

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find…

Machine Learning · Statistics 2018-11-20 Sebastian Ruder , Joachim Bingel , Isabelle Augenstein , Anders Søgaard

Although deep neural networks (DNNs) have demonstrated impressive results during the last decade, they remain highly specialized tools, which are trained -- often from scratch -- to solve each particular task. The human brain, in contrast,…

Neural and Evolutionary Computing · Computer Science 2019-08-22 Alexander V. Terekhov , Guglielmo Montone , J. Kevin O'Regan

Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Jathushan Rajasegaran , Vinoj Jayasundara , Sandaru Jayasekara , Hirunima Jayasekara , Suranga Seneviratne , Ranga Rodrigo

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

We introduce and train distributed neural architectures (DNA) in vision and language domains. DNAs are initialized with a proto-architecture that consists of (transformer, MLP, attention, etc.) modules and routers. Any token (or patch) can…

Machine Learning · Computer Science 2025-06-30 Aditya Cowsik , Tianyu He , Andrey Gromov

The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enormous number of parameters that must be trained (ranging from…

Machine Learning · Computer Science 2021-10-28 Subhabrata Dutta , Tanya Gautam , Soumen Chakrabarti , Tanmoy Chakraborty

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Linhao Qu , Shaolei Liu , Manning Wang , Zhijian Song