English
Related papers

Related papers: Position Coupling: Improving Length Generalization…

200 papers

Sequence modeling has important applications in natural language processing and computer vision. Recently, the transformer-based models have shown strong performance on various sequence modeling tasks, which rely on attention to capture…

Computation and Language · Computer Science 2023-05-09 Zhen Qin , Xiaodong Han , Weixuan Sun , Bowen He , Dong Li , Dongxu Li , Yuchao Dai , Lingpeng Kong , Yiran Zhong

Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform multiple, computationally distinct ICL tasks…

We introduce STRING: Separable Translationally Invariant Position Encodings. STRING extends Rotary Position Encodings, a recently proposed and widely used algorithm in large language models, via a unifying theoretical framework.…

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Computation and Language · Computer Science 2022-09-09 Markus Bayer , Marc-André Kaufhold , Christian Reuter

Machine learning has become a promising approach for molecular modeling. Positional quantities, such as interatomic distances and bond angles, play a crucial role in molecule physics. The existing works rely on careful manual design of…

Machine Learning · Computer Science 2022-11-24 Xiang Gao , Weihao Gao , Wenzhi Xiao , Zhirui Wang , Chong Wang , Liang Xiang

Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…

Computation and Language · Computer Science 2025-09-29 Runsong Zhao , Xin Liu , Xinyu Liu , Pengcheng Huang , Chunyang Xiao , Tong Xiao , Jingbo Zhu

Symbolic Mathematical tasks such as integration often require multiple well-defined steps and understanding of sub-tasks to reach a solution. To understand Transformers' abilities in such tasks in a fine-grained manner, we deviate from…

Artificial Intelligence · Computer Science 2021-04-30 Vishesh Agarwal , Somak Aditya , Navin Goyal

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, what…

Machine Learning · Computer Science 2023-10-31 Kensen Shi , Joey Hong , Manzil Zaheer , Pengcheng Yin , Charles Sutton

Transformers have achieved state-of-the-art performance in numerous tasks. In this paper, we propose a continuous-time formulation of transformers. Specifically, we consider a dynamical system whose governing equation is parametrized by…

Machine Learning · Computer Science 2025-02-03 Kelvin Kan , Xingjian Li , Stanley Osher

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights,…

Machine Learning · Computer Science 2024-10-17 Ekansh Sharma , Daniel M. Roy , Gintare Karolina Dziugaite

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Self-attention has emerged as a vital component of state-of-the-art sequence-to-sequence models for natural language processing in recent years, brought to the forefront by pre-trained bi-directional Transformer models. Its effectiveness is…

Machine Learning · Computer Science 2020-06-23 Hyoungwook Nam , Seung Byum Seo , Vikram Sharma Mailthody , Noor Michael , Lan Li

Learning-based methods in robotics hold the promise of generalization, but what can be done if a learned policy does not generalize to a new situation? In principle, if an agent can at least evaluate its own success (i.e., with a reward…

Robotics · Computer Science 2023-02-28 Ashvin Nair , Brian Zhu , Gokul Narayanan , Eugen Solowjow , Sergey Levine

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…

Computation and Language · Computer Science 2026-02-26 Eric Todd , Jannik Brinkmann , Rohit Gandikota , David Bau

A key module in neural transformer-based deep architectures is positional encoding. This module enables a suitable way to encode positional information as input for transformer neural layers. This success has been rooted in the use of…

Machine Learning · Computer Science 2025-12-23 Ezequiel Lopez-Rubio , Macoris Decena-Gimenez , Rafael Marcos Luque-Baena

The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used.…

Computer Vision and Pattern Recognition · Computer Science 2016-05-12 Florian Bernard , Johan Thunberg , Peter Gemmar , Frank Hertel , Andreas Husch , Jorge Goncalves

Multi-term floating-point addition appears in vector dot-product computations, matrix multiplications, and other forms of floating-point data aggregation. A critical step in multi-term floating point addition is the alignment of fractions…

Hardware Architecture · Computer Science 2024-10-30 Kosmas Alexandridis , Giorgos Dimitrakopoulos

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Xi Chen , Shiyang Zhou , Muqi Huang , Jiaxu Feng , Yun Xiong , Kun Zhou , Biao Yang , Yuhui Zhang , Huishuai Bao , Sijia Peng , Chuan Li , Feng Shi

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture…

Machine Learning · Computer Science 2024-03-19 Liu Yang , Kangwook Lee , Robert Nowak , Dimitris Papailiopoulos

Molecular datasets often suffer from a lack of data. It is well-known that gathering data is difficult due to the complexity of experimentation or simulation involved. Here, we leverage mutual information across different tasks in molecular…

Machine Learning · Computer Science 2024-05-06 Sung Moon Ko , Sumin Lee , Dae-Woong Jeong , Hyunseung Kim , Chanhui Lee , Soorin Yim , Sehui Han