中文
相关论文

相关论文: Emergence of Episodic Memory in Transformers: Char…

200 篇论文

Understanding connections between artificial and biological intelligent systems can reveal fundamental principles of general intelligence. While many artificial intelligence models have a neuroscience counterpart, such connections are…

计算与语言 · 计算机科学 2024-11-01 Li Ji-An , Corey Y. Zhou , Marcus K. Benna , Marcelo G. Mattar

Large language models (LLMs) exhibit strong in-context learning capabilities, but how they track and retrieve information from context remains underexplored. Drawing on the free recall paradigm in cognitive science (where participants…

计算与语言 · 计算机科学 2026-04-02 Anooshka Bajaj , Deven Mahesh Mistry , Sahaj Singh Maini , Yash Aggarwal , Billy Dickson , Zoran Tiganj

In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by…

计算与语言 · 计算机科学 2025-10-28 Anooshka Bajaj , Deven Mahesh Mistry , Sahaj Singh Maini , Yash Aggarwal , Zoran Tiganj

"Induction heads" are attention heads that implement a simple algorithm to complete token sequences like [A][B] ... [A] -> [B]. In this work, we present preliminary and indirect evidence for a hypothesis that induction heads might…

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

计算与语言 · 计算机科学 2022-06-03 Hao Peng , Jungo Kasai , Nikolaos Pappas , Dani Yogatama , Zhaofeng Wu , Lingpeng Kong , Roy Schwartz , Noah A. Smith

We investigate the integration of human-like working memory constraints into the Transformer architecture and implement several cognitively inspired attention variants, including fixed-width windows based and temporal decay based attention…

计算与语言 · 计算机科学 2026-04-24 Pranava Madhyastha , Dagmar Adamcova

Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal…

计算与语言 · 计算机科学 2024-09-18 Christian Clark , Byung-Doh Oh , William Schuler

Episodic memory plays a crucial role in various cognitive processes, such as the ability to mentally recall past events. While cognitive science emphasizes the significance of spatial context in the formation and retrieval of episodic…

机器学习 · 计算机科学 2024-03-04 Junmo Cho , Jaesik Yoon , Sungjin Ahn

Recent work in computational psycholinguistics has revealed intriguing parallels between attention mechanisms and human memory retrieval, focusing primarily on vanilla Transformers that operate on token-level representations. However,…

计算与语言 · 计算机科学 2025-08-20 Ryo Yoshida , Shinnosuke Isono , Kohei Kajikawa , Taiga Someya , Yushi Sugimoto , Yohei Oseki

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

人机交互 · 计算机科学 2019-06-14 Jesse Vig

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

计算与语言 · 计算机科学 2022-05-05 Guy D. Rosin , Kira Radinsky

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

机器学习 · 计算机科学 2024-03-05 Sadegh Mahdavi , Renjie Liao , Christos Thrampoulidis

For many years now, understanding the brain mechanism has been a great research subject in many different fields. Brain signal processing and especially electroencephalogram (EEG) has recently known a growing interest both in academia and…

神经元与认知 · 定量生物学 2022-04-18 Victor Delvigne , Hazem Wannous , Jean-Philippe Vandeborre , Laurence Ris , Thierry Dutoit

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

计算与语言 · 计算机科学 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

机器学习 · 计算机科学 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

Modeling of longitudinal cohort data typically involves complex temporal dependencies between multiple variables. There, the transformer architecture, which has been highly successful in language and vision applications, allows us to…

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

计算与语言 · 计算机科学 2026-05-20 Jiaoda Li , Ryan Cotterell

Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such…

机器学习 · 计算机科学 2025-10-24 Pulkit Gopalani , Wei Hu

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

机器学习 · 计算机科学 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

机器学习 · 计算机科学 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li
‹ 上一页 1 2 3 10 下一页 ›