Enhancing Context Through Contrast

no code implementations • 6 Jan 2024 • Kshitij Ambilduke, Aneesh Shetye, Diksha Bagade, Rishika Bhagwatkar, Khurshed Fitter, Prasad Vagdargi, Shital Chiddarwar

The language-dependent nature of language modelling introduces a trade-off between the universality of the learned representations and the model's performance on the language modelling tasks.

Contrastive Learning Language Modelling +2

Design and Development of Autonomous Delivery Robot

1 code implementation • 16 Mar 2021 • Aniket Gujarathi, Akshay Kulkarni, Unmesh Patil, Yogesh Phalak, Rajeshree Deotalu, Aman Jain, Navid Panchi, Ashwin Dhabale, Shital Chiddarwar

Autonomous robots are developed to be robust enough to work beside humans and to carry out jobs efficiently.

Data Efficient Stagewise Knowledge Distillation

1 code implementation • 15 Nov 2019 • Akshay Kulkarni, Navid Panchi, Sharath Chandra Raparthy, Shital Chiddarwar

We show, across the tested tasks, significant performance gains even with a fraction of the data used in distillation, without compromising on the metric.

Knowledge Distillation Model Compression +2