English
Related papers

Related papers: Associative-State Universal Transformers: Sparse R…

200 papers

Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…

Information Retrieval · Computer Science 2026-05-26 Jianrui Zhang , Hyun Jung Lee , Sukanta Ganguly , Tae-Eui Kam , Donghyun Kim , Yong Jae Lee

Sequence models lie at the heart of modern deep learning. However, rapid advancements have produced a diversity of seemingly unrelated architectures, such as Transformers and recurrent alternatives. In this paper, we introduce a unifying…

Machine Learning · Computer Science 2025-05-05 Ke Alexander Wang , Jiaxin Shi , Emily B. Fox

This paper focuses on reducing memory usage in enumerative model checking, while maintaining the multi-core scalability obtained in earlier work. We present a tree-based multi-core compression method, which works by leveraging sharing among…

Data Structures and Algorithms · Computer Science 2011-05-17 Alfons Laarman , Jaco van de Pol , Michael Weber

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Machine Learning · Computer Science 2026-05-15 Mayank Mishra , Shawn Tan , Ion Stoica , Joseph Gonzalez , Tri Dao

Popularized by the Differentiable Search Index, the emerging paradigm of generative retrieval re-frames the classic information retrieval problem into a sequence-to-sequence modeling task, forgoing external indices and encoding an entire…

Information Retrieval · Computer Science 2023-05-22 Ronak Pradeep , Kai Hui , Jai Gupta , Adam D. Lelkes , Honglei Zhuang , Jimmy Lin , Donald Metzler , Vinh Q. Tran

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Information Retrieval · Computer Science 2022-08-11 Dahlia Shehata , Negar Arabzadeh , Charles L. A. Clarke

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.…

Computation and Language · Computer Science 2021-09-17 Fei Xiao , Liang Pang , Yanyan Lan , Yan Wang , Huawei Shen , Xueqi Cheng

Structured shape completion recovers missing geometry as primitives rather than as unstructured points, which enables primitive-based surface reconstruction. Instead of following the prevailing cascade, we rethink how primitives and points…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Zhaiyu Chen , Yuqing Wang , Xiao Xiang Zhu

Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive models with fewer parameters often lag behind non-recursive…

Machine Learning · Computer Science 2026-04-21 Chengting Yu , Xiaobo Shu , Yadao Wang , Yizhen Zhang , Haoyi Wu , Jiaang Li , Rujiao Long , Ziheng Chen , Yuchi Xu , Wenbo Su , Bo Zheng

Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and…

Artificial Intelligence · Computer Science 2025-12-29 Zitian Gao , Lynx Chen , Yihao Xiao , He Xing , Ran Tao , Haoming Luo , Joey Zhou , Bryan Dai

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We present a unified framework that trains a single end-to-end ASR…

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Haiwen Diao , Bo Wan , Ying Zhang , Xu Jia , Huchuan Lu , Long Chen

Many algorithms use data structures that maintain properties of matrices undergoing some changes. The applications are wide-ranging and include for example matchings, shortest paths, linear programming, semi-definite programming, convex…

Data Structures and Algorithms · Computer Science 2020-10-28 Jan van den Brand

The standard sparse-autoencoder (SAE) interpretability protocol labels each feature from its top-activating contexts and validates by single-feature steering. We propose the pairwise matrix protocol, co-varying steering coefficient with…

Machine Learning · Computer Science 2026-05-06 Michael A. Riegler , Birk Sebastian Frostelid Torpmann-Hagen

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a recurrent architecture…

Machine Learning · Computer Science 2024-10-29 Anand Gopalakrishnan , Aleksandar Stanić , Jürgen Schmidhuber , Michael Curtis Mozer

Coherent systems are representative of many practical applications, ranging from infrastructure networks to supply chains. Probabilistic evaluation of such systems remains challenging, however, because existing decomposition-based methods…

Machine Learning · Computer Science 2026-04-21 Ji-Eun Byun , Hyeuk Ryu , Junho Song

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

End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…

Computation and Language · Computer Science 2023-03-21 Bolaji Yusuf , Aditya Gourav , Ankur Gandhe , Ivan Bulyko

State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured…