English
Related papers

Related papers: Quantifying Context Mixing in Transformers

200 papers

The performance of a cross-sectional currency strategy depends crucially on accurately ranking instruments prior to portfolio construction. While this ranking step is traditionally performed using heuristics, or by sorting the outputs…

Portfolio Management · Quantitative Finance 2022-01-31 Daniel Poh , Bryan Lim , Stefan Zohren , Stephen Roberts

How language models process complex input that requires multiple steps of inference is not well understood. Previous research has shown that information about intermediate values of these inputs can be extracted from the activations of the…

Machine Learning · Computer Science 2023-01-18 Yuta Matsumoto , Benjamin Heinzerling , Masashi Yoshikawa , Kentaro Inui

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Emiru Tsunoo , Yosuke Kashiwagi , Toshiyuki Kumakura , Shinji Watanabe

The integration of syntactic structures into Transformer machine translation has shown positive results, but to our knowledge, no work has attempted to do so with semantic structures. In this work we propose two novel parameter-free methods…

Computation and Language · Computer Science 2022-09-08 Aviv Slobodkin , Leshem Choshen , Omri Abend

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

Machine Learning · Computer Science 2026-05-19 Rushil Chandrupatla , Leo Bangayan , Sebastian Leng

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard…

Computation and Language · Computer Science 2022-05-30 James Lee-Thorp , Joshua Ainslie , Ilya Eckstein , Santiago Ontanon

Transformer models have become a promising approach for crop-type classification. Although their attention weights can be used to understand the relevant time points for crop disambiguation, the validity of these insights depends on how…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Ivica Obadic , Ribana Roscher , Dario Augusto Borges Oliveira , Xiao Xiang Zhu

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Yehao Li , Ting Yao , Yingwei Pan , Tao Mei

In-context learning (ICL) is a valuable capability exhibited by Transformers pretrained on diverse sequence tasks. However, previous studies have observed that ICL often conflicts with the model's inherent in-weight learning (IWL) ability.…

Machine Learning · Computer Science 2026-03-17 Guanyu Chen , Ruichen Wang , Tianren Zhang , Feng Chen

Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike more structured texts like news, chat conversations are…

Computation and Language · Computer Science 2024-03-14 Sweta Agrawal , Amin Farajian , Patrick Fernandes , Ricardo Rei , André F. T. Martins

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Machine Learning · Computer Science 2024-06-05 Hongkang Li , Meng Wang , Tengfei Ma , Sijia Liu , Zaixi Zhang , Pin-Yu Chen

Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Frieda Born , Tom Neuhäuser , Lukas Muttenthaler , Brett D. Roads , Bernhard Spitzer , Andrew K. Lampinen , Matt Jones , Klaus-Robert Müller , Michael C. Mozer

We study transformers' in-context learning of variable-length Markov chains (VOMCs), focusing on the finite-sample accuracy as the number of in-context examples increases. Compared to fixed-order Markov chains (FOMCs), learning VOMCs is…

Machine Learning · Computer Science 2026-04-01 Ruida Zhou , Chao Tian , Suhas Diggavi

Self-modulating mechanisms introduce dynamic adaptation capabilities within language models through contextual realignment strategies that influence token embedding trajectories across extended sequences. Contextual Flux is explored as an…

Computation and Language · Computer Science 2025-08-11 Henry Evidail , Zachary Mountebank , Alistair Hathersage , Peter Stanhope , Basil Ravenscroft , Tobias Waddingham

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and…

Machine Learning · Computer Science 2025-08-12 Xinyi Wu , Yifei Wang , Stefanie Jegelka , Ali Jadbabaie

By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words…

Sound · Computer Science 2023-08-16 Tianyi Xu , Zhanheng Yang , Kaixun Huang , Pengcheng Guo , Ao Zhang , Biao Li , Changru Chen , Chao Li , Lei Xie

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only…

Machine Learning · Computer Science 2026-02-06 Jiecheng Lu , Xu Han , Yan Sun , Viresh Pati , Yubin Kim , Siddhartha Somani , Shihao Yang

Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a single dominant signal. We propose a rank-aware multi-encoder framework that selectively…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Junghyun Lee , Hyunseo Kim , Hanna Jang , Junhyug Noh

Recent approaches to the Automatic Post-Editing (APE) research have shown that better results are obtained by multi-source models, which jointly encode both source (src) and machine translation output (mt) to produce post-edited sentence…

Computation and Language · Computer Science 2019-08-19 WonKee Lee , Junsu Park , Byung-Hyun Go , Jong-Hyeok Lee

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer…

Machine Learning · Computer Science 2024-05-31 Francesco Petri , Luigi Asprino , Aldo Gangemi
‹ Prev 1 4 5 6 7 8 10 Next ›