English
Related papers

Related papers: Transformer as an Euler Discretization of Score-ba…

200 papers

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-28 Rui Wang , Junyi Ao , Long Zhou , Shujie Liu , Zhihua Wei , Tom Ko , Qing Li , Yu Zhang

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

Computation and Language · Computer Science 2026-03-10 J. Clayton Kerce , Alexis Fox

We reconstruct the velocity field of incompressible flows given a finite set of measurements. For the spatial approximation, we introduce the Sparse Fourier divergence-free (SFdf) approximation based on a discrete $L^2$ projection. Within…

Fluid Dynamics · Physics 2021-10-13 Luis Espath , Dmitry Kabanov , Jonas Kiessling , Raúl Tempone

Traffic flow forecasting is essential and challenging to intelligent city management and public safety. Recent studies have shown the potential of convolution-free Transformer approach to extract the dynamic dependencies among complex…

Physics and Society · Physics 2021-11-08 Xiao Yan , Xianghua Gan , Jingjing Tang , Rui Wang

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the…

Machine Learning · Computer Science 2026-05-22 Athanasios Zeris

This paper introduces a high-order Markov chain task to investigate how transformers learn to integrate information from multiple past positions with varying statistical significance. We demonstrate that transformers learn this task…

Machine Learning · Computer Science 2026-02-24 Oğuz Kaan Yüksel , Rodrigo Alvarez Lucendo , Nicolas Flammarion

Density estimation, a central problem in machine learning, can be performed using Normalizing Flows (NFs). NFs comprise a sequence of invertible transformations, that turn a complex target distribution into a simple one, by exploiting the…

Machine Learning · Computer Science 2024-01-04 Massimiliano Patacchiola , Aliaksandra Shysheya , Katja Hofmann , Richard E. Turner

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

Machine Learning · Computer Science 2021-08-06 Dmitry Baranchuk , Vladimir Aliev , Artem Babenko

Recently normalizing flows have been gaining traction in text-to-speech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce…

Sound · Computer Science 2023-12-29 Jakub Mosiński , Piotr Biliński , Thomas Merritt , Abdelhamid Ezzerg , Daniel Korzekwa

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…

Computation and Language · Computer Science 2021-04-02 Yunyang Xiong , Zhanpeng Zeng , Rudrasis Chakraborty , Mingxing Tan , Glenn Fung , Yin Li , Vikas Singh

The quadratic computational cost of the self-attention mechanism is a primary challenge in scaling Transformer models. While attention sparsity is widely studied as a technique to improve computational efficiency, it is almost universally…

Computation and Language · Computer Science 2025-08-11 Sagar Gandhi , Vishal Gandhi

Transformer-based language models have set new benchmarks across a wide range of NLP tasks, yet reliably estimating the uncertainty of their predictions remains a significant challenge. Existing uncertainty estimation (UE) techniques often…

Machine Learning · Computer Science 2024-09-18 Elizaveta Kostenok , Daniil Cherniavskii , Alexey Zaytsev

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Malvina Nikandrou , Georgios Pantazopoulos , Ioannis Konstas , Alessandro Suglia

Transformer architectures excel at sequential modeling yet remain fundamentally limited by correlational learning - they capture spurious associations induced by latent confounders rather than invariant causal mechanisms. We identify this…

Machine Learning · Computer Science 2026-03-17 Charles Luo

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in…

Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet speech front-end tasks such as speech enhancement (SE), target…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-12 Ziqian Wang , Zikai Liu , Yike Zhu , Xingchen Li , Boyi Kang , Jixun Yao , Xianjun Xia , Chuanzeng Huang , Lei Xie

The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo…

Machine Learning · Statistics 2020-10-27 Hao Wu , Jonas Köhler , Frank Noé

The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational complexity and lacks grounding in biological neural computation. We propose Selective…

Machine Learning · Computer Science 2026-02-17 Hasi Hays