English
Related papers

Related papers: Fusion Matters: Length-Aware Analysis of Positiona…

200 papers

Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merging has emerged as a solution to increase computational…

Machine Learning · Computer Science 2025-08-06 Leon Götz , Marcel Kollovieh , Stephan Günnemann , Leo Schwinn

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…

Computation and Language · Computer Science 2022-03-16 Xiangyang Mou , Mo Yu , Bingsheng Yao , Lifu Huang

Even for simple arithmetic tasks like integer addition, it is challenging for Transformers to generalize to longer sequences than those encountered during training. To tackle this problem, we propose position coupling, a simple yet…

Machine Learning · Computer Science 2024-10-31 Hanseul Cho , Jaeyoung Cha , Pranjal Awasthi , Srinadh Bhojanapalli , Anupam Gupta , Chulhee Yun

As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Takeru Miyato , Bernhard Jaeger , Max Welling , Andreas Geiger

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

This paper proposes a learning model, based on rank-fusion graphs, for general applicability in multimodal prediction tasks, such as multimodal regression and image classification. Rank-fusion graphs encode information from multiple…

Computer Vision and Pattern Recognition · Computer Science 2020-07-06 Icaro Cavalcante Dourado , Salvatore Tabbone , Ricardo da Silva Torres

Fusion is a technique for merging multiple independently-trained neural networks in order to combine their capabilities. Past attempts have been restricted to the case of fully-connected, convolutional, and residual networks. This paper…

Machine Learning · Computer Science 2024-04-23 Moritz Imfeld , Jacopo Graldi , Marco Giordano , Thomas Hofmann , Sotiris Anagnostidis , Sidak Pal Singh

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this…

Machine Learning · Computer Science 2024-06-05 Mahdi Sabbaghi , George Pappas , Hamed Hassani , Surbhi Goel

Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in…

Machine Learning · Computer Science 2025-11-13 Freya Behrens , Luca Biggio , Lenka Zdeborová

Recent top-performing temporal 3D detectors based on Lidars have increasingly adopted region-based paradigms. They first generate coarse proposals, followed by encoding and fusing regional features. However, indiscriminate sampling and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Chenxu Dang , Zaipeng Duan , Pei An , Xinmin Zhang , Xuzhong Hu , Jie Ma

In this work, we present a generalized formulation of the Transformer algorithm by reinterpreting its core mechanisms within the framework of Path Integral formalism. In this perspective, the attention mechanism is recast as a process that…

High Energy Physics - Phenomenology · Physics 2025-05-02 Won-Gi Paeng , Daesuk Kwon , Kyungwon Jeong , Honggyo Suh

The representation, or encoding, utilized in evolutionary algorithms has a substantial effect on their performance. Examination of the suitability of widely used representations for quality diversity optimization (QD) in robotic domains has…

Neural and Evolutionary Computing · Computer Science 2023-04-10 Ludovico Scarton , Alexander Hagg

Training transformer-based encoder-decoder models for long document summarization poses a significant challenge due to the quadratic memory consumption during training. Several approaches have been proposed to extend the input length at…

Computation and Language · Computer Science 2025-06-30 Rohit Saxena , Hao Tang , Frank Keller

SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. We are interested in knowing how such a translation-invariant convolutional generator could capture the global…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Rui Xu , Xintao Wang , Kai Chen , Bolei Zhou , Chen Change Loy

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Computation and Language · Computer Science 2025-08-11 Alistair Dombrowski , Beatrix Engelhardt , Dimitri Fairbrother , Henry Evidail

Generating a readable summary that describes the functionality of a program is known as source code summarization. In this task, learning code representation by modeling the pairwise relationship between code tokens to capture their…

Software Engineering · Computer Science 2020-05-05 Wasi Uddin Ahmad , Saikat Chakraborty , Baishakhi Ray , Kai-Wei Chang

Transformers have achieved remarkable success in medical image analysis owing to their powerful capability to use flexible self-attention mechanism. However, due to lacking intrinsic inductive bias in modeling visual structural information,…

Image and Video Processing · Electrical Eng. & Systems 2022-11-18 Yiyue Hu , Lei Zhang , Nan Mu , Lei Liu

Graph Transformers (GTs) facilitate the comprehension of graph-structured data by calculating the self-attention of node pairs without considering node position information. To address this limitation, we introduce an innovative and…

Machine Learning · Computer Science 2023-12-12 Kushal Bose , Swagatam Das

In this paper, we introduce a method called graph fusion embedding, designed for multi-graph embedding with shared vertex sets. Under the framework of supervised learning, our method exhibits a remarkable and highly desirable synergistic…

Social and Information Networks · Computer Science 2024-06-27 Cencheng Shen , Carey E. Priebe , Jonathan Larson , Ha Trinh

We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an…

Machine Learning · Computer Science 2024-11-01 Konstantinos Kogkalidis , Jean-Philippe Bernardy , Vikas Garg