English
Related papers

Related papers: Look-Ahead Removal for Top-Down Tree Transducers

200 papers

Transformer models have demonstrated exceptional performance across a wide range of applications. Though forming the foundation of Transformer models, the dot-product attention does not scale well to long-context data since its time…

Machine Learning · Computer Science 2025-03-14 Yongchang Hao , Mengyao Zhai , Hossein Hajimirsadeghi , Sepidehsadat Hosseini , Frederick Tung

As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in simple beam search to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-24 Wei Zhou , Ralf Schlüter , Hermann Ney

Deep learning models such as the Transformer are often constructed by heuristics and experience. To provide a complementary foundation, in this work we study the following problem: Is it possible to find an energy function underlying the…

Machine Learning · Computer Science 2023-02-28 Yongyi Yang , Zengfeng Huang , David Wipf

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and…

Computer Vision and Pattern Recognition · Computer Science 2017-07-13 Yahui Liu , Jian Yao , Li Li , Xiaohu Lu , Jing Han

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency. However, their quadratic computational complexity poses a major obstacle for applying them to vision tasks requiring…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Shitao Tang , Jiahui Zhang , Siyu Zhu , Ping Tan

As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this…

Machine Learning · Computer Science 2020-11-02 Hila Levi , Shimon Ullman

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: in the geometry of the residual stream, and in stack-like attention patterns maintaining…

Computation and Language · Computer Science 2026-04-27 Aryan Sharma , Cutter Dawes , Shivam Raval

Multilinear Discriminant Analysis (MDA) is a powerful dimension reduction method specifically formulated to deal with tensor data. Precisely, the goal of MDA is to find mode-specific projections that optimally separate tensor data from…

Numerical Analysis · Mathematics 2022-03-03 F. Dufrenois , A. El Ichi , K. Jbilou

Interpretability is an important aspect of the trustworthiness of a model's predictions. Transformer's predictions are widely explained by the attention weights, i.e., a probability distribution generated at its self-attention unit (head).…

Computation and Language · Computer Science 2021-06-03 Rishabh Bhardwaj , Navonil Majumder , Soujanya Poria , Eduard Hovy

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Computation and Language · Computer Science 2018-11-02 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Modern societies have developed insatiable demands for more computation capabilities. Exploiting implicit parallelism to provide automatic performance improvement remains a central goal in engineering future general-purpose computing…

Hardware Architecture · Computer Science 2018-12-14 Sushant Kondguli , Michael Huang

An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of attention called relational cross-attention. The approach is…

Machine Learning · Statistics 2024-04-16 Awni Altabaa , Taylor Webb , Jonathan Cohen , John Lafferty

We present a comprehensive classical and parameterized complexity analysis of decision tree pruning operations, extending recent research on the complexity of learning small decision trees. Thereby, we offer new insights into the…

Machine Learning · Computer Science 2025-03-06 Juha Harviainen , Frank Sommer , Manuel Sorge , Stefan Szeider

Some genes can change their relative locations in a genome. Thus for different individuals of the same species, the orders of genes might be different. Such jumping genes are called transposons. A practical problem is to determine…

Genomics · Quantitative Biology 2022-09-02 Yue Wang

Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource…

Computation and Language · Computer Science 2023-10-23 Ofir Arviv , Dmitry Nikolaev , Taelin Karidi , Omri Abend

Deterministic two-way transducers define the robust class of regular functions which is, among other good properties, closed under composition. However, the best known algorithms for composing two-way transducers cause a double exponential…

Formal Languages and Automata Theory · Computer Science 2017-02-24 Luc Dartois , Paulin Fournier , Ismaël Jecker , Nathan Lhote

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity…

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Bowen Pan , Rameswar Panda , Yifan Jiang , Zhangyang Wang , Rogerio Feris , Aude Oliva