v1v2 (latest)

Fundamental Limitations on Subquadratic Alternatives to Transformers

5 October 2024

Papers citing "Fundamental Limitations on Subquadratic Alternatives to Transformers"

42 / 42 papers shown

Title
Two Heads Are Better than One: Simulating Large Transformers with Small Ones Hantao Yu Josh Alman 33 0 0 13 Jun 2025
SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance Teerapong Panboonyuen 153 0 0 12 Jun 2025
Subquadratic Algorithms and Hardness for Attention with Any Temperature Shreya Gupta Boyang Huang Barna Saha Yinzhan Xu Christopher Ye 66 2 0 20 May 2025
Compression Barriers for Autoregressive Transformers Themistoklis Haris Krzysztof Onak 79 1 0 21 Feb 2025
Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models Jerry Yao-Chieh Hu Maojiang Su En-Jui Kuo Zhao Song Han Liu 89 29 0 05 Jun 2024
Transformers, parallel computation, and logarithmic depth Clayton Sanford Daniel J. Hsu Matus Telgarsky 75 42 0 14 Feb 2024
On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis Jerry Yao-Chieh Hu Thomas Lin Zhao Song Han Liu 98 41 0 07 Feb 2024
Mamba: Linear-Time Sequence Modeling with Selective State Spaces Albert Gu Tri Dao Mamba 168 2,839 0 01 Dec 2023
What Formal Languages Can Transformers Express? A Survey Lena Strobl William Merrill Gail Weiss David Chiang Dana Angluin AI4CE 113 60 0 01 Nov 2023
The Expressive Power of Transformers with Chain of Thought William Merrill Ashish Sabharwal LRM AI4CE ReLM 105 41 0 11 Oct 2023
HyperAttention: Long-context Attention in Near-Linear Time Insu Han Rajesh Jayaram Amin Karbasi Vahab Mirrokni David P. Woodruff A. Zandieh 116 74 0 09 Oct 2023
Representational Strengths and Limitations of Transformers Clayton Sanford Daniel J. Hsu Matus Telgarsky 76 93 0 05 Jun 2023
GPT-4 Technical Report OpenAI OpenAI OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad ... Shengjia Zhao Tianhao Zheng Juntang Zhuang William Zhuk Barret Zoph LLMAG MLLM 1.6K 14,852 0 15 Mar 2023
Fast Attention Requires Bounded Entries Josh Alman Zhao Song 106 86 0 26 Feb 2023
KDEformer: Accelerating Transformers via Kernel Density Estimation A. Zandieh Insu Han Majid Daliri Amin Karbasi 125 47 0 05 Feb 2023
Transformers Learn Shortcuts to Automata Bingbin Liu Jordan T. Ash Surbhi Goel A. Krishnamurthy Cyril Zhang OffRL LRM 161 178 0 19 Oct 2022
On The Computational Complexity of Self-Attention Feyza Duman Keles Pruthuvi Maheshakya Wijewardena Chinmay Hegde 144 130 0 11 Sep 2022
Formal Algorithms for Transformers Mary Phuong Marcus Hutter 62 75 0 19 Jul 2022
Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity Sophie Hao Dana Angluin Robert Frank 85 80 0 13 Apr 2022
Overcoming a Theoretical Limitation of Self-Attention David Chiang Peter A. Cholak 110 84 0 24 Feb 2022
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers Colin Wei Yining Chen Tengyu Ma 79 92 0 28 Jul 2021
Saturated Transformers are Constant-Depth Threshold Circuits William Merrill Ashish Sabharwal Noah A. Smith 118 107 0 30 Jun 2021
Self-Attention Networks Can Process Bounded Hierarchical Languages Shunyu Yao Binghui Peng Christos H. Papadimitriou Karthik Narasimhan 89 83 0 24 May 2021
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai ... Matthias Minderer G. Heigold Sylvain Gelly Jakob Uszkoreit N. Houlsby ViT 770 41,877 0 22 Oct 2020
SMYRF: Efficient Attention using Asymmetric Clustering Giannis Daras Nikita Kitaev Augustus Odena A. Dimakis 106 46 0 11 Oct 2020
Rethinking Attention with Performers K. Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane ... Afroz Mohiuddin Lukasz Kaiser David Belanger Lucy J. Colwell Adrian Weller 198 1,605 0 30 Sep 2020
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention Angelos Katharopoulos Apoorv Vyas Nikolaos Pappas Franccois Fleuret 218 1,800 0 29 Jun 2020
Linformer: Self-Attention with Linear Complexity Sinong Wang Belinda Z. Li Madian Khabsa Han Fang Hao Ma 247 1,720 0 08 Jun 2020
Language Models are Few-Shot Learners Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan ... Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever Dario Amodei BDL 1.2K 42,712 0 28 May 2020
End-to-End Object Detection with Transformers Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov Sergey Zagoruyko ViT 3DV PINN 509 13,230 0 26 May 2020
Synthesizer: Rethinking Self-Attention in Transformer Models Yi Tay Dara Bahri Donald Metzler Da-Cheng Juan Zhe Zhao Che Zheng 76 342 0 02 May 2020
Longformer: The Long-Document Transformer Iz Beltagy Matthew E. Peters Arman Cohan RALM VLM 230 4,109 0 10 Apr 2020
Efficient Content-Based Sparse Attention with Routing Transformers Aurko Roy M. Saffar Ashish Vaswani David Grangier MoE 405 606 0 12 Mar 2020
Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection Xiaoyi Gu Leman Akoglu Alessandro Rinaldo 149 96 0 08 Jul 2019
XLNet: Generalized Autoregressive Pretraining for Language Understanding Zhilin Yang Zihang Dai Yiming Yang J. Carbonell Ruslan Salakhutdinov Quoc V. Le AI4CE 372 8,464 0 19 Jun 2019
Theoretical Limitations of Self-Attention in Neural Sequence Models Michael Hahn 94 276 0 16 Jun 2019
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin Ming-Wei Chang Kenton Lee Kristina Toutanova VLM SSL SSeg 1.9K 95,604 0 11 Oct 2018
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clément Hongler 376 3,226 0 20 Jun 2018
Spectrally-normalized margin bounds for neural networks Peter L. Bartlett Dylan J. Foster Matus Telgarsky ODL 350 1,225 0 26 Jun 2017
Attention Is All You Need Ashish Vaswani Noam M. Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan Gomez Lukasz Kaiser Illia Polosukhin 3DV 980 133,429 0 12 Jun 2017
Distributed Representations of Sentences and Documents Quoc V. Le Tomas Mikolov FaML 395 9,267 0 16 May 2014
On the Number of Linear Regions of Deep Neural Networks Guido Montúfar Razvan Pascanu Kyunghyun Cho Yoshua Bengio 106 1,256 0 08 Feb 2014