English
Related papers

Related papers: Priming: Hybrid State Space Models From Pre-traine…

200 papers

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, many challenges remain in training deep transformer networks,…

Computation and Language · Computer Science 2025-12-09 Zhijian Zhuo , Yutao Zeng , Ya Wang , Sijun Zhang , Jian Yang , Xiaoqing Li , Xun Zhou , Jinwen Ma

Recent advancements in State Space Models (SSMs) have attracted significant interest, particularly in models optimized for parallel training and handling long-range dependencies. Architectures like Mamba have scaled to billions of…

Machine Learning · Computer Science 2024-10-22 Zheng Zhan , Yushu Wu , Zhenglun Kong , Changdi Yang , Yifan Gong , Xuan Shen , Xue Lin , Pu Zhao , Yanzhi Wang

Hybrid sequence models--combining Transformer and state-space model layers--seek to gain the expressive versatility of attention as well as the computational efficiency of state-space model layers. Despite burgeoning interest in hybrid…

Machine Learning · Computer Science 2026-03-11 John Cooper , Ilias Diakonikolas , Mingchen Ma , Frederic Sala

Recent works have demonstrated that attention-based transformer and large language model (LLM) architectures can achieve strong channel state prediction (CSP) performance by capturing long-range temporal dependencies across channel state…

Information Theory · Computer Science 2026-04-27 Aladin Djuhera , Haris Gacanin , Holger Boche

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Xinyu Wang , Jinghua Hou , Zhe Liu , Yingying Zhu

Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all contextual information into a fixed-size state, leading to…

Computation and Language · Computer Science 2026-01-14 Yingfa Chen , Xinrong Zhang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

Machine Learning · Computer Science 2024-04-02 Ameen Ali , Itamar Zimerman , Lior Wolf

Effective reasoning is crucial to solving complex mathematical problems. Recent large language models (LLMs) have boosted performance by scaling test-time computation through long chain-of-thought reasoning. However, transformer-based…

Machine Learning · Computer Science 2025-09-10 Junxiong Wang , Wen-Ding Li , Daniele Paliotta , Daniel Ritter , Alexander M. Rush , Tri Dao

Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of…

Machine Learning · Computer Science 2025-12-01 Abdullah Al Asif , Mobina Kashaniyan , Sixing Yu , Juan Pablo Muñoz , Ali Jannesari

Hybrid language models combining attention with state space models (SSMs) or linear attention offer improved efficiency, but whether both components are genuinely utilized remains unclear. We present a functional component ablation…

Computation and Language · Computer Science 2026-03-25 Hector Borobia , Elies Seguí-Mas , Guillermina Tormo-Carbó

State-space models (SSMs) have emerged as efficient alternatives to Transformers for sequence modeling, offering superior scalability through recurrent structures. However, their training remains costly and the ecosystem around them is far…

Machine Learning · Computer Science 2025-10-24 Penghao Wang , Yuhao Zhou , Mengxuan Wu , Panpan Zhang , Zhangyang Wang , Kai Wang

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Siavash Shams , Sukru Samet Dindar , Xilin Jiang , Nima Mesgarani

State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple yet effective trick…

Machine Learning · Computer Science 2025-05-28 Woomin Song , Jihoon Tack , Sangwoo Mo , Seunghyuk Oh , Jinwoo Shin

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer…

Computation and Language · Computer Science 2025-04-23 Zhichao Xu , Jinghua Yan , Ashim Gupta , Vivek Srikumar

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

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Xuanyu Lin , Xiaona Zeng , Xianwei Zheng , Xutao Li

State Space Models (SSMs) have emerged as an appealing alternative to Transformers for large language models, achieving state-of-the-art accuracy with constant memory complexity which allows for holding longer context lengths than…

Machine Learning · Computer Science 2024-12-10 Hung-Yueh Chiang , Chi-Chih Chang , Natalia Frumkin , Kai-Chiang Wu , Diana Marculescu

The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Filippo Botti , Alex Ergasti , Leonardo Rossi , Tomaso Fontanini , Claudio Ferrari , Massimo Bertozzi , Andrea Prati

Transformers excel at in-context retrieval but suffer from quadratic complexity with sequence length, while State Space Models (SSMs) offer efficient linear-time processing but have limited retrieval capabilities. We investigate whether…

Artificial Intelligence · Computer Science 2026-03-04 Georgios Pantazopoulos , Malvina Nikandrou , Ioannis Konstas , Alessandro Suglia

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large…

Computation and Language · Computer Science 2026-05-19 Xuan Zhang , Fengzhuo Zhang , Cunxiao Du , Chao Du , Tianyu Pang , Wei Gao , Min Lin