Search Results for author: Madan Musuvathi

Found 5 papers, 1 papers with code

Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions

no code implementations7 Apr 2023 Sarah Fakhoury, Saikat Chakraborty, Madan Musuvathi, Shuvendu K. Lahiri

Several benchmarks have recently emerged to evaluate the ability of LLMs to generate functionally correct code from natural language intent with respect to a set of hidden test cases.

TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches

2 code implementations8 Nov 2021 Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, Rachee Singh

TACCL uses a novel communication sketch abstraction to get crucial information from the designer to significantly reduce the search space and guide the synthesizer towards better algorithms.

GenderRobustness: Robustness of Gender Detection in Facial Recognition Systems with variation in Image Properties

no code implementations18 Nov 2020 Sharadha Srinivasan, Madan Musuvathi

In recent times, there have been increasing accusations on artificial intelligence systems and algorithms of computer vision of possessing implicit biases.

Scaling Distributed Training with Adaptive Summation

no code implementations4 Jun 2020 Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Olli Saarikivi, Tianju Xu, Vadim Eksarevskiy, Jaliya Ekanayake, Emad Barsoum

This paper introduces a novel method to combine gradients called Adasum (for adaptive sum) that converges faster than prior work.

Distributed Training of Embeddings using Graph Analytics

no code implementations8 Sep 2019 Gurbinder Gill, Roshan Dathathri, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Olli Saarikivi

This paper presents a distributed training framework for a class of applications that use Skip-gram-like models to generate embeddings.

Graph Generation Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.