English
Related papers

Related papers: InfiniMotion: Mamba Boosts Memory in Transformer f…

200 papers

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

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

Human motion understanding is a fundamental task with diverse practical applications, facilitated by the availability of large-scale motion capture datasets. Recent studies focus on text-motion tasks, such as text-based motion generation,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Xinghan Wang , Zixi Kang , Yadong Mu

Text-to-motion generation has gained increasing attention, but most existing methods are limited to generating short-term motions that correspond to a single sentence describing a single action. However, when a text stream describes a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-04 Zhao Yang , Bing Su , Ji-Rong Wen

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is…

Machine Learning · Computer Science 2024-10-29 Yang Dai , Oubo Ma , Longfei Zhang , Xingxing Liang , Shengchao Hu , Mengzhu Wang , Shouling Ji , Jincai Huang , Li Shen

With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computational demands associated with existing transformer-based Large…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Hosu Lee , Junho Kim , Hyunjun Kim , Yong Man Ro

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level…

Machine Learning · Computer Science 2025-04-11 Assaf Ben-Kish , Itamar Zimerman , Shady Abu-Hussein , Nadav Cohen , Amir Globerson , Lior Wolf , Raja Giryes

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-29 Xiangyu Zhang , Qiquan Zhang , Hexin Liu , Tianyi Xiao , Xinyuan Qian , Beena Ahmed , Eliathamby Ambikairajah , Haizhou Li , Julien Epps

We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Boshen Xu , Zihan Xiao , Jiaze Li , Jianzhong Ju , Zhenbo Luo , Jian Luan , Qin Jin

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Machine Learning · Computer Science 2025-10-07 Youjin Wang , Yangjingyi Chen , Jiahao Yan , Jiaxuan Lu , Xiao Sun

Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces…

Machine Learning · Computer Science 2024-06-28 Aobo Liang , Xingguo Jiang , Yan Sun , Xiaohou Shi , Ke Li

We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Jinyoung Park , Hee-Seon Kim , Kangwook Ko , Minbeom Kim , Changick Kim

Despite the significant role text-to-motion (T2M) generation plays across various applications, current methods involve a large number of parameters and suffer from slow inference speeds, leading to high usage costs. To address this, we aim…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Ling-An Zeng , Guohong Huang , Gaojie Wu , Wei-Shi Zheng

Recent advancements in imitation learning, particularly with the integration of LLM techniques, are set to significantly improve robots' dexterity and adaptability. This paper proposes using Mamba, a state-of-the-art architecture with…

Robotics · Computer Science 2024-09-26 Toshiaki Tsuji

Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world. However, designing an effective 4D backbone…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Jiuming Liu , Jinru Han , Lihao Liu , Angelica I. Aviles-Rivero , Chaokang Jiang , Zhe Liu , Hesheng Wang

Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address…

Machine Learning · Computer Science 2025-11-25 Liyuan Deng , Yunpeng Bai , Yongkang Dai , Xiaoshui Huang , Hongping Gan , Dongshuo Huang , Hao jiacheng , Yilei Shi

Human-human motion generation is essential for understanding humans as social beings. Current methods fall into two main categories: single-person-based methods and separate modeling-based methods. To delve into this field, we abstract the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Yabiao Wang , Shuo Wang , Jiangning Zhang , Ke Fan , Jiafu Wu , Zhucun Xue , Yong Liu

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yunze Liu , Peiran Wu , Cheng Liang , Junxiao Shen , Limin Wang , Li Yi

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…

Computation and Language · Computer Science 2025-01-03 Danlong Yuan , Jiahao Liu , Bei Li , Huishuai Zhang , Jingang Wang , Xunliang Cai , Dongyan Zhao

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

Hardware Architecture · Computer Science 2025-08-06 Dongho Yoon , Gungyu Lee , Jaewon Chang , Yunjae Lee , Dongjae Lee , Minsoo Rhu