English
Related papers

Related papers: Measuring Affinity between Attention-Head Weight S…

200 papers

Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. Originally developed as a scalable alternative to Gaussian Processes (GPs), which are…

Machine Learning · Computer Science 2026-04-20 Daniel Jenson , Jhonathan Navott , Mengyan Zhang , Makkunda Sharma , Elizaveta Semenova , Seth Flaxman

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Machine Learning · Computer Science 2024-12-25 Tianyu Ruan , Shihua Zhang

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov

Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family…

Machine Learning · Computer Science 2026-01-21 Luis Rosario Freytes

In recent years, task arithmetic has garnered increasing attention. This approach edits pre-trained models directly in weight space by combining the fine-tuned weights of various tasks into a unified model. Its efficiency and…

Machine Learning · Computer Science 2025-01-30 Ruochen Jin , Bojian Hou , Jiancong Xiao , Weijie Su , Li Shen

It is proven that encoding images and videos through Symmetric Positive Definite (SPD) matrices, and considering the Riemannian geometry of the resulting space, can lead to increased classification performance. Taking into account manifold…

Computer Vision and Pattern Recognition · Computer Science 2016-03-16 Azadeh Alavi , Vishal M Patel , Rama Chellappa

We present a novel dual-head deep learning architecture for protein-protein interaction modeling that enables simultaneous prediction of binding affinity ($\Delta G$) and mutation-induced affinity changes ($\Delta\Delta G$) using only…

Quantitative Methods · Quantitative Biology 2025-09-30 Supantha Dey , Ratul Chowdhury

Interpretability is an important aspect of the trustworthiness of a model's predictions. Transformer's predictions are widely explained by the attention weights, i.e., a probability distribution generated at its self-attention unit (head).…

Computation and Language · Computer Science 2021-06-03 Rishabh Bhardwaj , Navonil Majumder , Soujanya Poria , Eduard Hovy

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Hyeon Cho , Junyong Choi , Geonwoo Baek , Wonjun Hwang

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Sitong Wu , Tianyi Wu , Haoru Tan , Guodong Guo

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…

Multi-scale detection plays an important role in object detection models. However, researchers usually feel blank on how to reasonably configure detection heads combining multi-scale features at different input resolutions. We find that…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yi Shi , Jiang Wu , Shixuan Zhao , Gangyao Gao , Tao Deng , Hongmei Yan

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Computation and Language · Computer Science 2020-08-14 Madhura Pande , Aakriti Budhraja , Preksha Nema , Pratyush Kumar , Mitesh M. Khapra

The combination of neural network potential (NNP) with molecular simulations plays an important role in an efficient and thorough understanding of a molecular system's potential energy surface (PES). However, grasping the interplay between…

Computational Physics · Physics 2021-10-28 Ji Woong Yu , Min Young Ha , Bumjoon Seo , Won Bo Lee

Atomistic machine learning focuses on the creation of models which obey fundamental symmetries of atomistic configurations, such as permutation, translation, and rotation invariances. In many of these schemes, translation and rotation…

Inter-GPU communication has become a major bottleneck for modern AI workloads as models scale and improvements in hardware compute throughput outpace improvements in interconnect bandwidth. Existing systems mitigate this through…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Stuart H. Sul , Simran Arora , Benjamin F. Spector , Christopher Ré

Many statistical estimation techniques for high-dimensional or functional data are based on a preliminary dimension reduction step, which consists in projecting the sample $\bX_1, \hdots, \bX_n$ onto the first $D$ eigenvectors of the…

Statistics Theory · Mathematics 2010-04-26 Gérard Biau , André Mas

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

As high-performance computing (HPC) systems rapidly evolve, with increasing on-node parallelism and widespread use of accelerators, understanding how the code maps to hardware is essential for reaching optimal performance. Benchmarks are…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-11 Michael McKinsey , Stephanie Brink , Olga Pearce