English
Related papers

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

200 papers

Large Language Models (LLMs) achieve remarkable reasoning capabilities through transformer architectures with attention mechanisms. However, transformers suffer from quadratic time and memory complexity in the attention module (MHA) and…

The "state" of State Space Models (SSMs) represents their memory, which fades exponentially over an unbounded span. By contrast, Attention-based models have "eidetic" (i.e., verbatim, or photographic) memory over a finite span (context…

Computation and Language · Computer Science 2025-05-27 Elvis Nunez , Luca Zancato , Benjamin Bowman , Aditya Golatkar , Wei Xia , Stefano Soatto

The typical Selective State-Space Model (SSM) used in Mamba addresses several limitations of Transformers, such as the quadratic computational complexity with respect to sequence length and the significant memory requirements during…

Computation and Language · Computer Science 2025-10-24 Shengkun Tang , Liqun Ma , Haonan Li , Mingjie Sun , Zhiqiang Shen

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

Computation and Language · Computer Science 2026-04-08 Zhen Cheng , Hao-Bo Yang , Wan-Yi Huang , Jin-Long Li

State Space Models (SSMs) are efficient alternatives to traditional sequence models, excelling at processing long sequences with lower computational complexity. Their reliance on matrix multiplications makes them ideal for compute-in-memory…

Hardware Architecture · Computer Science 2025-08-19 Yuannuo Feng , Wenyong Zhou , Yuexi Lyu , Hanjie Liu , Zhengwu Liu , Ngai Wong , Wang Kang

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Machine Learning · Computer Science 2025-01-29 J. Pablo Muñoz , Jinjie Yuan , Nilesh Jain

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

Transformers and Mamba, initially invented for natural language processing, have inspired backbone architectures for visual recognition. Recent studies integrated Local Attention Transformers with Mamba to capture both local details and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Meng Lou , Yunxiang Fu , Yizhou Yu

State-space models (SSMs) have emerged as an efficient strategy for building powerful language models, avoiding the quadratic complexity of computing attention in transformers. Despite their promise, the interpretability and steerability of…

Machine Learning · Computer Science 2026-05-22 Vamshi Sunku Mohan , Kaustubh Gupta , Aneesha Das , Chandan Singh

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Xiuwei Chen , Wentao Hu , Xiao Dong , Sihao Lin , Zisheng Chen , Meng Cao , Yina Zhuang , Jianhua Han , Hang Xu , Xiaodan Liang

Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a…

Systems and Control · Electrical Eng. & Systems 2026-04-28 Hiroki Fujii , Masaki Yamakita

State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand,…

Computation and Language · Computer Science 2026-04-17 Abhinav Moudgil , Ningyuan Huang , Eeshan Gunesh Dhekane , Pau Rodríguez , Luca Zappella , Federico Danieli

In recent years, there has been a growing interest in integrating linear state-space models (SSM) in deep neural network architectures of foundation models. This is exemplified by the recent success of Mamba, showing better performance than…

Systems and Control · Electrical Eng. & Systems 2024-03-26 Carmen Amo Alonso , Jerome Sieber , Melanie N. Zeilinger

Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically…

Artificial Intelligence · Computer Science 2025-11-12 Hieu Tran , Zonghai Yao , Nguyen Luong Tran , Zhichao Yang , Feiyun Ouyang , Shuo Han , Razieh Rahimi , Hong Yu

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning.…

Machine Learning · Computer Science 2026-04-07 Haohao Qu , Liangbo Ning , Rui An , Wenqi Fan , Tyler Derr , Hui Liu , Xin Xu , Qing Li

Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text…

Computation and Language · Computer Science 2025-02-25 Sam Blouir , Jimmy T. H. Smith , Antonios Anastasopoulos , Amarda Shehu

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Neil Rathi , Nikil Roashan Selvam , Róbert Csordás , Dan Jurafsky , Christopher Potts

State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. In this paper, we propose a multi-head state space (MH-SSM)…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-29 Yassir Fathullah , Chunyang Wu , Yuan Shangguan , Junteng Jia , Wenhan Xiong , Jay Mahadeokar , Chunxi Liu , Yangyang Shi , Ozlem Kalinli , Mike Seltzer , Mark J. F. Gales

Hybrid model architectures that combine computational primitives (e.g., Attention, MLP) in different ratios have shown promising performance beyond Transformers. Some studies have shown that different interleavings of primitives can affect…

Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational…

Computation and Language · Computer Science 2026-04-22 Sangmin Bae , Bilge Acun , Chien-Yu Lin , Haroun Habeeb , Seungyeon Kim , Liang Luo , Junjie Wang , Carole-Jean Wu