no code implementations • 21 Aug 2023 • Sumeet S. Singh
Examining Transformers through this perspective reveals key insights, establishing a Theory of Transformers: 1) Intelligent behaviours map to paths in Embedding Space which, the Transformer random-walks through during inferencing.
5 code implementations • 11 Mar 2021 • Sumeet S. Singh, Sergey Karayev
We present a Neural Network based Handwritten Text Recognition (HTR) model architecture that can be trained to recognize full pages of handwritten or printed text without image segmentation.
Ranked #11 on Handwritten Text Recognition on IAM
1 code implementation • 15 Feb 2018 • Sumeet S. Singh
We present a neural transducer model with visual attention that learns to generate LaTeX markup of a real-world math formula given its image.
Ranked #1 on Optical Character Recognition (OCR) on im2latex-100k