English
Related papers

Related papers: Your representations are in the network: composabl…

200 papers

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a…

Image and Video Processing · Electrical Eng. & Systems 2021-10-07 Peng Liu , Charlie T. Tran , Bin Kong , Ruogu Fang

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts:…

While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we…

Computation and Language · Computer Science 2020-09-30 Xiaoya Li , Yuxian Meng , Mingxin Zhou , Qinghong Han , Fei Wu , Jiwei Li

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Xialei Liu , Xusheng Cao , Haori Lu , Jia-wen Xiao , Andrew D. Bagdanov , Ming-Ming Cheng

Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Yi-Lin Sung , Jaemin Cho , Mohit Bansal

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method that learns weight updates $\Delta W = AB$ for pretrained weights $W$ through low-rank adapters $A$ and $B$. While LoRA ensures hardware efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Yibo Zhong , Jinman Zhao , Yao Zhou

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Amelie Royer , Christoph H. Lampert

In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. More specifically, a token selector parses the current…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Manish Kumar Singh , Rajeev Yasarla , Hong Cai , Mingu Lee , Fatih Porikli

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Computation and Language · Computer Science 2025-09-19 Yanming Kang , Giang Tran , Hans De Sterck

Deep learning based end-to-end multi-channel speech enhancement methods have achieved impressive performance by leveraging sub-band, cross-band, and spatial information. However, these methods often demand substantial computational…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-18 Yaokai Zhang , Hanchen Pei , Wanqi Wang , Gongping Huang

Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions…

Computation and Language · Computer Science 2024-02-09 Abhishek Panigrahi , Sadhika Malladi , Mengzhou Xia , Sanjeev Arora

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Parth Kothari , Danya Li , Yuejiang Liu , Alexandre Alahi

Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle variations among highly-confused categories. Most existing…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Tian Zhang , Dongliang Chang , Zhanyu Ma , Jun Guo

Res-Tuning introduces a flexible and efficient paradigm for model tuning, showing that tuners decoupled from the backbone network can achieve performance comparable to traditional methods. Existing methods commonly construct the tuner as a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Chaojie Mao , Zeyinzi Jiang

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Samyak Jha , Junho Kim

Recently, multiple architectures has been proposed to improve the efficiency of the Transformer Language Models through changing the design of the self-attention block to have a linear-cost inference (LCI). A notable approach in this realm…

Computation and Language · Computer Science 2024-04-04 Sehyun Choi

Recent research has shown that Transformers with linear attention are capable of in-context learning (ICL) by implementing a linear estimator through gradient descent steps. However, the existing results on the optimization landscape apply…

Machine Learning · Computer Science 2024-07-16 Yingcong Li , Ankit Singh Rawat , Samet Oymak

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected weight matrices. In this work, we compare the performance of…

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is randomly initialized and data-agnostic, discarding potentially…

Machine Learning · Computer Science 2026-01-07 Yuan Yin , Shashanka Venkataramanan , Tuan-Hung Vu , Andrei Bursuc , Matthieu Cord
‹ Prev 1 4 5 6 7 8 10 Next ›