Subquadratic Algorithms and Hardness for Attention with Any Temperature

20 May 2025

Papers citing "Subquadratic Algorithms and Hardness for Attention with Any Temperature"

4 / 4 papers shown

Title
Minimalist Softmax Attention Provably Learns Constrained Boolean Functions Jerry Yao-Chieh Hu Xiwen Zhang Maojiang Su Zhao Song Han Liu MLT 240 1 0 26 May 2025
Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse Josh Alman Zhao Song 101 2 0 22 May 2025
Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness Hao Xuan Bokai Yang Xingyu Li AAML 93 4 0 28 Feb 2025
Fundamental Limitations on Subquadratic Alternatives to Transformers Josh Alman Hantao Yu 110 4 0 05 Oct 2024