English
Related papers

Related papers: Hamming Attention Distillation: Binarizing Keys an…

200 papers

Knowledge distillation (KD) has been a ubiquitous method for model compression to strengthen the capability of a lightweight model with the transferred knowledge from the teacher. In particular, KD has been employed in quantization-aware…

Computation and Language · Computer Science 2022-11-22 Minsoo Kim , Sihwa Lee , Sukjin Hong , Du-Seong Chang , Jungwook Choi

Attention-based Neural Networks (NN) have demonstrated their effectiveness in accurate memory access prediction, an essential step in data prefetching. However, the substantial computational overheads associated with these models result in…

Neural and Evolutionary Computing · Computer Science 2024-02-23 Pengmiao Zhang , Neelesh Gupta , Rajgopal Kannan , Viktor K. Prasanna

Diffusion models have demonstrated significant applications in the field of image generation. However, their high computational and memory costs pose challenges for deployment. Model quantization has emerged as a promising solution to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Shizhuo Mao , Hongtao Zou , Qihu Xie , Song Chen , Yi Kang

Large language models have become a vital component in modern NLP, achieving state of the art performance in a variety of tasks. However, they are often inefficient for real-world deployment due to their expensive inference costs. Knowledge…

Computation and Language · Computer Science 2023-10-16 Takuma Udagawa , Aashka Trivedi , Michele Merler , Bishwaranjan Bhattacharjee

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…

Computer Vision and Pattern Recognition · Computer Science 2025-02-05 Karam Park , Jae Woong Soh , Nam Ik Cho

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Computation and Language · Computer Science 2024-10-15 Guangxuan Xiao , Jiaming Tang , Jingwei Zuo , Junxian Guo , Shang Yang , Haotian Tang , Yao Fu , Song Han

Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference efficient. Aggregate benchmarks suggest that this works but they hide selective failures.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yihao Liang , Niraj K. Jha

Slim attention shrinks the context memory size by 2x for transformer models with MHA (multi-head attention), which can speed up inference by up to 2x for large context windows. Slim attention is an exact, mathematically identical…

Machine Learning · Computer Science 2025-06-04 Nils Graef , Andrew Wasielewski

Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism. Here we propose an approach to deal with two key existing challenges: the high computational…

Machine Learning · Computer Science 2021-10-20 Dhruv Agarwal , Tanay Agrawal , Laura M. Ferrari , François Bremond

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Xuerui Zhang , Xuehao Wang , Zhan Zhuang , Linglan Zhao , Ziyue Li , Xinmin Zhang , Zhihuan Song , Yu Zhang

Researchers have long tried to minimize training costs in deep learning while maintaining strong generalization across diverse datasets. Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Ahmad Sajedi , Samir Khaki , Ehsan Amjadian , Lucy Z. Liu , Yuri A. Lawryshyn , Konstantinos N. Plataniotis

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

Machine Learning · Computer Science 2026-02-04 Mahyar Alinejad , Yue Wang , George Atia

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Computation and Language · Computer Science 2024-12-30 Shuo Wang , Chihang Wang , Jia Gao , Zhen Qi , Hongye Zheng , Xiaoxuan Liao

Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps to improve the performance of the student network. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Ziyao Guo , Haonan Yan , Hui Li , Xiaodong Lin

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms…

Computation and Language · Computer Science 2022-10-12 Ilias Chalkidis , Xiang Dai , Manos Fergadiotis , Prodromos Malakasiotis , Desmond Elliott

Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leverage pre-trained diffusion models' robust feature extraction…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Yeqi He , Liang Li , Zhiwen Yang , Xichun Sheng , Zhidong Zhao , Chenggang Yan

Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint…

Computation and Language · Computer Science 2026-03-30 Juan Gabriel Kostelec , Xiang Wang , Axel Laborieux , Christos Sourmpis , Qinghai Guo

Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Arne F. Nix , Max F. Burg , Fabian H. Sinz

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong