paper-with-me

Papers

Formal Algorithms for Transformers

2022-07-19 · Mary Phuong, Marcus Hutter

This document aims to be a self-contained, mathematically precise overview of transformer architectures and algorithms (*not* results). It covers what transformers are, how they are trained, what they are used for, their key architectural components, and a preview of the most prominent models. The reader is assumed to be familiar with basic ML terminology and simpler neural network architectures such as MLPs.

📄 PDF Abstract BibTeX arXiv:2207.09238

Code (1)

myazdani/formal-algorithms-for-transformers pytorch

Similar Papers 제목 키워드 기반

From Scientific Texts to Verifiable Code: Automating the Process with Transformers

2025-01-09 · Changjie Wang, Mariano Scazzariello, Marco Chiesa

Despite the vast body of research literature proposing algorithms with formal guarantees, the amount of verifiable code in today's systems remains minimal. This discrepancy stems from the inherent difficulty of verifying…

Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers

2024-04-05 · Andy Yang, David Chiang

Deriving formal bounds on the expressivity of transformers, as well as studying transformers that are constructed to implement known algorithms, are both effective methods for better understanding the computational power…

Conformal prediction for text infilling and part-of-speech prediction

2021-11-04 · Neil Dey, Jing Ding, Jack Ferrell, Carolina Kapper 외

Modern machine learning algorithms are capable of providing remarkably accurate point-predictions; however, questions remain about their statistical reliability. Unlike conventional machine learning methods, conformal pr…

Conformal PredictionPOSPOS TaggingPrediction+2

Discovering Interpretable Algorithms by Decompiling Transformers to RASP

2026-02-09 · Xinting Huang, Aleksandra Bakalova, Satwik Bhattamishra, William Merrill 외 arxiv

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization a…

Can Transformers Learn to Solve Problems Recursively?

2023-05-24 · Shizhuo Dylan Zhang, Curt Tigges, Stella Biderman, Maxim Raginsky 외

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to wh…