no code implementations • 31 Oct 2022 • Pratik Kayal, Mrinal Anand, Harsh Desai, Mayank Singh
In this paper, we adapt the transformer-based language modeling paradigm for scientific table structure and content extraction.
no code implementations • 3 Nov 2021 • Mrinal Anand, Aditya Garg
Supervised learning requires a large amount of labeled data to reach state-of-the-art performance.
no code implementations • 22 Oct 2021 • Mrinal Anand, Nidhin Harilal, Chandan Kumar, Shanmuganathan Raman
We first extract clean LDR frames from noisy LDR video with alternating exposures with a denoising network trained in a self-supervised setting.
no code implementations • NeurIPS Workshop AIPLANS 2021 • Mrinal Anand, Pratik Kayal, Mayank Singh
Program synthesis from natural language descriptions is a challenging task.
no code implementations • NeurIPS Workshop AIPLANS 2021 • Mrinal Anand, Pratik Kayal, Mayank Singh
The resurgence of automatic program synthesis has been observed with the rise of deep learning.
no code implementations • 22 Jun 2021 • Mrinal Anand, Pratik Kayal, Mayank Singh
In this paper, we specifically experiment with \textsc{AlgoLisp} DSL-based generative models and showcase the existence of significant dataset bias through different classes of adversarial examples.
no code implementations • 30 May 2021 • Pratik Kayal, Mrinal Anand, Harsh Desai, Mayank Singh
This paper discusses the dataset, tasks, participants' methods, and results of the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX.