English
Related papers

Related papers: Multi-layer Cross-attention is Provably Optimal fo…

200 papers

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We…

Artificial Intelligence · Computer Science 2020-11-13 Aya Abdelsalam Ismail , Mahmudul Hasan , Faisal Ishtiaq

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol…

Artificial Intelligence · Computer Science 2020-10-23 Vladimir Mikulik , Grégoire Delétang , Tom McGrath , Tim Genewein , Miljan Martic , Shane Legg , Pedro A. Ortega

Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the…

Machine Learning · Statistics 2025-02-27 Pierre Marion , Raphaël Berthier , Gérard Biau , Claire Boyer

We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First,…

Machine Learning · Computer Science 2020-06-16 Kiran Lekkala , Laurent Itti

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in…

Machine Learning · Computer Science 2024-11-21 Ismail Nejjar , Faez Ahmed , Olga Fink

Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior training. It has been argued that this capability, known as in-context learning (ICL), is a…

Machine Learning · Statistics 2025-10-06 Yue M. Lu , Mary I. Letey , Jacob A. Zavatone-Veth , Anindita Maiti , Cengiz Pehlevan

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…

Machine Learning · Computer Science 2019-01-23 Yun Zeng

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

Computation and Language · Computer Science 2018-08-07 Patrick Huber , Jan Niehues , Alex Waibel

Attention-based neural networks such as transformers have demonstrated a remarkable ability to exhibit in-context learning (ICL): Given a short prompt sequence of tokens from an unseen task, they can formulate relevant per-token and…

Machine Learning · Statistics 2023-10-23 Ruiqi Zhang , Spencer Frei , Peter L. Bartlett

Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextual signals are unevenly beneficial across sentences. Existing training objectives do not…

Computation and Language · Computer Science 2026-03-27 Ying Li , Xinglin Lyu , Junhui Li , Jinlong Yang , Hengchao Shang , Min Zhang , Shimin Tao , Daimeng Wei

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…

Computation and Language · Computer Science 2021-09-15 Mozhdeh Gheini , Xiang Ren , Jonathan May

In-context learning (ICL) has garnered significant attention for its ability to grasp functions/tasks from demonstrations. Recent studies suggest the presence of a latent task/function vector in LLMs during ICL. Merullo et al. (2024) showed…

Machine Learning · Computer Science 2025-08-14 Dake Bu , Wei Huang , Andi Han , Atsushi Nitanda , Qingfu Zhang , Hau-San Wong , Taiji Suzuki

Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities, enabling them to solve unseen tasks solely based on input contexts without adjusting model parameters. In this paper, we study ICL in one of…

Machine Learning · Statistics 2024-03-18 Jingfeng Wu , Difan Zou , Zixiang Chen , Vladimir Braverman , Quanquan Gu , Peter L. Bartlett

The starting point of our network architecture is the Credibility Transformer which extends the classical Transformer architecture by a credibility mechanism to improve model learning and predictive performance. This Credibility Transformer…

Machine Learning · Computer Science 2026-01-15 Kishan Padayachy , Ronald Richman , Salvatore Scognamiglio , Mario V. Wüthrich

Pre-trained transformers exhibit the capability of adapting to new tasks through in-context learning (ICL), where they efficiently utilize a limited set of prompts without explicit model optimization. The canonical communication problem of…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

Computation and Language · Computer Science 2025-12-11 Ning Lyu , Yuxi Wang , Feng Chen , Qingyuan Zhang

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning within a much broader spectrum of…

Computation and Language · Computer Science 2025-06-06 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Aaditya K. Singh , Murray Shanahan

Traditionally, neural network training has been primarily viewed as an approximation of maximum likelihood estimation (MLE). This interpretation originated in a time when training for multiple epochs on small datasets was common and…

Machine Learning · Computer Science 2024-10-03 Samuel Müller , Noah Hollmann , Frank Hutter

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating simple binary…

Machine Learning · Computer Science 2026-03-13 Faris Chaudhry , Siddhant Gadkari