English
Related papers

Related papers: Flash STU: Fast Spectral Transform Units

200 papers

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on…

Computation and Language · Computer Science 2022-10-20 Shuo Xie , Jiahao Qiu , Ankita Pasad , Li Du , Qing Qu , Hongyuan Mei

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

Modern large language models are built on sequence modeling via next-token prediction. While the Transformer remains the dominant architecture for sequence modeling, its quadratic decoding complexity in sequence length poses a major…

Machine Learning · Computer Science 2024-10-03 Bo Liu , Rui Wang , Lemeng Wu , Yihao Feng , Peter Stone , Qiang Liu

Transformer-based architectures have achieved remarkable success in natural language processing and computer vision. However, their performance in multivariate long-term forecasting often falls short compared to simpler linear baselines.…

Machine Learning · Computer Science 2025-07-09 Dizhen Liang

The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Jingjun Yang , Liangwei Fan , Jinpu Zhang , Xiangkai Lian , Hui Shen , Dewen Hu

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir

State-space models (SSMs), such as Mamba (Gu & Dao, 2023), have been proposed as alternatives to Transformer networks in language modeling, by incorporating gating, convolutions, and input-dependent token selection to mitigate the quadratic…

Machine Learning · Computer Science 2024-04-26 Jongho Park , Jaeseung Park , Zheyang Xiong , Nayoung Lee , Jaewoong Cho , Samet Oymak , Kangwook Lee , Dimitris Papailiopoulos

Transformer-based models are the state-of-the-art for Natural Language Understanding (NLU) applications. Models are getting bigger and better on various tasks. However, Transformer models remain computationally challenging since they are…

Computation and Language · Computer Science 2020-10-27 Young Jin Kim , Hany Hassan Awadalla

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

Stereo matching methods based on iterative optimization, like RAFT-Stereo and IGEV-Stereo, have evolved into a cornerstone in the field of stereo matching. However, these methods struggle to simultaneously capture high-frequency information…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Xianqi Wang , Gangwei Xu , Hao Jia , Xin Yang

Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba, that…

Machine Learning · Computer Science 2026-03-12 Morris Yau , Sharut Gupta , Valerie Engelmayer , Kazuki Irie , Stefanie Jegelka , Jacob Andreas

Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Nursena Köprücü , Destiny Okpekpe , Antonio Orvieto

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Computation and Language · Computer Science 2024-07-09 Hugo Pitorro , Pavlo Vasylenko , Marcos Treviso , André F. T. Martins

Recent deep learning models increasingly rely on depth without structural guarantees on the validity of intermediate representations, rendering early stopping and adaptive computation ill-posed. We address this limitation by formulating a…

Machine Learning · Computer Science 2026-01-28 Geunhyeok Yu , Hyoseok Hwang

The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data. An overarching challenge to this date is client heterogeneity, which may arise not only from…

Video large language models have demonstrated strong video understanding capabilities but suffer from high inference costs due to the massive number of tokens in long videos. Inspired by event-based vision, we propose an event-guided,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Wenhao Xu , Xin Dong , Yue Li , Haoyuan Shi , Zhiwei Xiong

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Machine Learning · Computer Science 2026-05-15 Mayank Mishra , Shawn Tan , Ion Stoica , Joseph Gonzalez , Tri Dao

Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propose an efficient FL approach that capitalizes on additional…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-09 Juncheng Jia , Ji Liu , Chao Huo , Yihui Shen , Yang Zhou , Huaiyu Dai , Dejing Dou

Spatial-Temporal Graph (STG) forecasting on large-scale networks has garnered significant attention. However, existing models predominantly focus on short-horizon predictions and suffer from notorious computational costs and memory…

Machine Learning · Computer Science 2026-01-09 Yiji Zhao , Zihao Zhong , Ao Wang , Haomin Wen , Ming Jin , Yuxuan Liang , Huaiyu Wan , Hao Wu

3D Swin Transformer (3D-ST) known for its hierarchical attention and window-based processing, excels in capturing intricate spatial relationships within images. Spatial-spectral Transformer (SST), meanwhile, specializes in modeling…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Muhammad Ahmad , Manuel Mazzara , Salvatore Distifano