English
Related papers

Related papers: Linear-Time and Constant-Memory Text Embeddings Ba…

200 papers

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Information Retrieval · Computer Science 2025-05-08 Qianru Zhang , Liang Qu , Honggang Wen , Dong Huang , Siu-Ming Yiu , Nguyen Quoc Viet Hung , Hongzhi Yin

Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases, these models suffer from catastrophic geometric forgetting and accumulation drift,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Tianchen Deng , Zhenxiang Xiong , Nailin Wang , Fangjinhua Wang , Jiuming Liu , Jianfei Yang , Hesheng Wang

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yanhua Zhang , Ke Zhang , Jingyu Wang , Gabriella Balestra , Samanta Rosati , Yulin Wu , Wuwei Wang , Valentina Giannini

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…

Computation and Language · Computer Science 2025-03-10 Simran Arora , Sabri Eyuboglu , Michael Zhang , Aman Timalsina , Silas Alberti , Dylan Zinsley , James Zou , Atri Rudra , Christopher Ré

Transformers have generally supplanted recurrent neural networks as the dominant architecture for both natural language processing tasks and for modelling the effect of predictability on online human language comprehension. However, two…

Computation and Language · Computer Science 2024-08-27 James A. Michaelov , Catherine Arnett , Benjamin K. Bergen

We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle…

Machine Learning · Computer Science 2025-02-25 Aviv Bick , Tobias Katsch , Nimit Sohoni , Arjun Desai , Albert Gu

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-16 Tan Dat Nguyen , Sangmin Bae , Joon Son Chung , Ji-Hoon Kim

Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations,…

Machine Learning · Computer Science 2024-04-10 Gonçalo Paulo , Thomas Marshall , Nora Belrose

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Machine Learning · Computer Science 2024-06-04 Sili Huang , Jifeng Hu , Zhejian Yang , Liwei Yang , Tao Luo , Hechang Chen , Lichao Sun , Bo Yang

In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Qiyan Zhao , Yue Yan , Da-Han Wang

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Computation and Language · Computer Science 2024-10-22 Wangjie You , Zecheng Tang , Juntao Li , Lili Yao , Min Zhang

Over the last two decades, language modeling has experienced a shift from the use of predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Haobo Yuan , Xiangtai Li , Lu Qi , Tao Zhang , Ming-Hsuan Yang , Shuicheng Yan , Chen Change Loy

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of the most critical…

The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…

Machine Learning · Computer Science 2025-05-26 Josh Alman , Hantao Yu

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…

Machine Learning · Computer Science 2026-03-20 Youjin Wang , Jiaqiao Zhao , Rong Fu , Run Zhou , Ruizhe Zhang , Jiani Liang , Suisuai Cao , Feng Zhou