Vision Transformers provably learn spatial structure

13 October 2022

Papers citing "Vision Transformers provably learn spatial structure"

20 / 20 papers shown

Title
Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights Zhaiming Shen Alex Havrilla Rongjie Lai A. Cloninger Wenjing Liao 39 0 0 06 May 2025
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers Hongkang Li Yihua Zhang Shuai Zhang M. Wang Sijia Liu Pin-Yu Chen MoMe 60 2 0 15 Apr 2025
Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks Chenyang Zhang Peifeng Gao Difan Zou Yuan Cao OOD MLT 59 0 0 11 Apr 2025
PViT: Prior-augmented Vision Transformer for Out-of-distribution Detection Tianhao Zhang Zhixiang Chen Lyudmila Mihaylova 74 0 0 27 Oct 2024
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent Bo Chen Xiaoyu Li Yingyu Liang Zhenmei Shi Zhao-quan Song 83 19 0 15 Oct 2024
Locality Alignment Improves Vision-Language Models Ian Covert Tony Sun James Y. Zou Tatsunori Hashimoto VLM 64 3 0 14 Oct 2024
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li Yuanzhi Li OOD 28 2 0 11 Oct 2024
Attention layers provably solve single-location regression P. Marion Raphael Berthier Gérard Biau Claire Boyer 81 2 0 02 Oct 2024
Are queries and keys always relevant? A case study on Transformer wave functions Riccardo Rende Luciano Loris Viteritti 24 5 0 29 May 2024
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers Lorenzo Tiberi Francesca Mignacco Kazuki Irie H. Sompolinsky 42 6 0 24 May 2024
Implicit Bias and Fast Convergence Rates for Self-attention Bhavya Vasudeva Puneesh Deora Christos Thrampoulidis 24 13 0 08 Feb 2024
An Information-Theoretic Analysis of In-Context Learning Hong Jun Jeon Jason D. Lee Qi Lei Benjamin Van Roy 15 18 0 28 Jan 2024
Memorization Capacity of Multi-Head Attention in Transformers Sadegh Mahdavi Renjie Liao Christos Thrampoulidis 22 22 0 03 Jun 2023
Patches Are All You Need? Asher Trockman J. Zico Kolter ViT 214 400 0 24 Jan 2022
CMT: Convolutional Neural Networks Meet Vision Transformers Jianyuan Guo Kai Han Han Wu Yehui Tang Chunjing Xu Yunhe Wang Chang Xu ViT 337 500 0 13 Jul 2021
Intriguing Properties of Vision Transformers Muzammal Naseer Kanchana Ranasinghe Salman Khan Munawar Hayat F. Khan Ming-Hsuan Yang ViT 251 618 0 21 May 2021
Emerging Properties in Self-Supervised Vision Transformers Mathilde Caron Hugo Touvron Ishan Misra Hervé Jégou Julien Mairal Piotr Bojanowski Armand Joulin 298 5,761 0 29 Apr 2021
LambdaNetworks: Modeling Long-Range Interactions Without Attention Irwan Bello 260 178 0 17 Feb 2021
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning Yuhuai Wu M. Rabe Wenda Li Jimmy Ba Roger C. Grosse Christian Szegedy AIMat LRM 61 51 0 15 Jan 2021
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016