English
Related papers

Related papers: Token Turing Machines

200 papers

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Kabir Swain , Sijie Han , Daniel Karl I. Weidele , Mauro Martino , Antonio Torralba

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…

Machine Learning · Computer Science 2025-01-03 Ali Behrouz , Peilin Zhong , Vahab Mirrokni

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yancheng Wang , Yingzhen Yang

Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as…

Machine Learning · Computer Science 2020-10-06 Jiahao Su , Wonmin Byeon , Jean Kossaifi , Furong Huang , Jan Kautz , Animashree Anandkumar

Medical image segmentation is essential for clinical diagnosis and treatment planning. Although transformer-based methods have achieved remarkable results, their high computational cost hinders clinical deployment. To address this issue, we…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yaxuan Jiao , Qing Xu , Yuxiang Luo , Xiangjian He , Zhen Chen , Wenting Duan

In distributed function computation, each node has an initial value and the goal is to compute a function of these values in a distributed manner. In this paper, we propose a novel token-based approach to compute a wide class of target…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-03-28 Saber Salehkaleybar , S. Jamaloddin Golestani

Large language models are typically controlled via prompts, which must be repeatedly re-processed for every new query and are difficult to reuse modularly. We introduce TokMem, a procedural memory framework that compiles each reusable task…

Computation and Language · Computer Science 2026-03-10 Zijun Wu , Yongchang Hao , Lili Mou

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

Machine Learning · Computer Science 2026-05-27 Youngin Kim , Ray Sun , Inho Kim , Bumsoo Park , Hyun Oh Song

Multimodal foundation models (MFMs) have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. However, these models face inherent limitations due to their finite internal…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Xingjian Diao , Chunhui Zhang , Weiyi Wu , Zhongyu Ouyang , Peijun Qing , Ming Cheng , Soroush Vosoughi , Jiang Gui

We introduce a new type of generalized Turing machines (GTMs), which are intended as a tool for the mathematician who studies computability in Analysis. In a single tape cell a GTM can store a symbol, a real number, a continuous real…

Logic · Mathematics 2015-07-01 Nazanin Tavana , Klaus Weihrauch

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Yunfei Li , Yuezun Li , Baoyuan Wu , Junyu Dong , Guopu Zhu , Siwei Lyu

We propose DEEPMEMORY, a novel deep architecture for sequence-to-sequence learning, which performs the task through a series of nonlinear transformations from the representation of the input sequence (e.g., a Chinese sentence) to the final…

Computation and Language · Computer Science 2016-01-08 Fandong Meng , Zhengdong Lu , Zhaopeng Tu , Hang Li , Qun Liu

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

Computation and Language · Computer Science 2022-04-27 Haozhe Ji , Rongsheng Zhang , Zhenyu Yang , Zhipeng Hu , Minlie Huang

Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…

Machine Learning · Computer Science 2025-03-14 Joni-Kristian Kämäräinen

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Machine Learning · Computer Science 2021-08-19 Radostin Cholakov , Todor Kolev

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

Machine Learning · Computer Science 2025-08-19 Parsa Omidi , Xingshuai Huang , Axel Laborieux , Bahareh Nikpour , Tianyu Shi , Armaghan Eshaghi

Human motion prediction is a necessary component for many applications in robotics and autonomous driving. Recent methods propose using sequence-to-sequence deep learning models to tackle this problem. However, they do not focus on…

Computer Vision and Pattern Recognition · Computer Science 2020-10-08 Tim Lebailly , Sena Kiciroglu , Mathieu Salzmann , Pascal Fua , Wei Wang

Breakthroughs in deep learning and memory networks have made major advances in natural language understanding. Language is sequential and information carried through the sequence can be captured through memory networks. Learning the…

Computation and Language · Computer Science 2023-05-22 Anupiya Nugaliyadde

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Over the past few decades, the hydrology community has witnessed notable advancements in streamflow prediction, particularly with the introduction of cutting-edge machine-learning algorithms. Recurrent neural networks, especially Long…

Machine Learning · Computer Science 2023-05-23 Sinan Rasiya Koya , Tirthankar Roy