What is my math transformer doing? -- Three results on interpretability and generalization

31 October 2022

Papers citing "What is my math transformer doing? -- Three results on interpretability and generalization"

5 / 5 papers shown

Title
Looped ReLU MLPs May Be All You Need as Practical Programmable Computers Yingyu Liang Zhizhou Sha Zhenmei Shi Zhao Song Yufa Zhou 101 18 0 21 Feb 2025
Generating particle physics Lagrangians with transformers Yong Sheng Koay Rikard Enberg Stefano Moretti Eliel Camargo-Molina 44 0 0 17 Jan 2025
Positional Description Matters for Transformers Arithmetic Ruoqi Shen Sébastien Bubeck Ronen Eldan Yin Tat Lee Yuanzhi Li Yi Zhang 42 38 0 22 Nov 2023
Looped Transformers are Better at Learning Learning Algorithms Liu Yang Kangwook Lee Robert D. Nowak Dimitris Papailiopoulos 29 24 0 21 Nov 2023
Controllable Neural Symbolic Regression Tommaso Bendinelli Luca Biggio Pierre-Alexandre Kamienny 36 14 0 20 Apr 2023