Avinash Madasu

Avinash Madasu
Santa Clara, CA

[Note that I have stopped updating this website. Visit my Google Scholar or LinkedIN or Resume/CV on the links below for current status].

I am a staff research scientist at Intel AI Labs working on multi-modal AI. I graduated from University of North Carolina, Chapel Hill with a Master in Computer Science advised by Prof. Gedas Bertasius. While at UNC, my research focused on multi-modal AI.

I was a senior engineer at Samsung R & D Institute India - Bangalore, for 3 years where I worked on Bixby (Samsung's voice assistant). My job was to design NLU models to help improve Bixby. I had the opportunity to work under Prof. Asif Eqbal on multi-modal dialog systems. I graduated from National Institute of Technology Tiruchirappalli with Bachelors in Computer Science. While pursuing UG studies, I worked closely with Prof. Sivasankar on statistical feature extraction techniques for sentiment analysis.

I am interested in contributing to open source frameworks that empower neural networks. I am also a member of Distributed Deep Machine Learning Community and reviewer of gluonnlp, Amazon's NLP library.

Research Interests

My area of interests lie in Multi-modal AI especially in the intersection of Natural Language Processing, Computer Vision and Robotics. I had worked in the areas of multi-modal dialog systems, domain adaptation, text classification etc.

Press

The Jerusalem Post (10M viewership) - https://www.jpost.com/special-content/leading-computer-science-expert-avinash-madasu-recounts-his-formative-experiences-in-the-field-749910
Outlook India (16.8M viewership)- https://www.outlookindia.com/business-spotlight/avinash-madasu-s-work-boosted-bixby-s-value-proposition-but-that-was-just-the-start-news-286468/amp
Analytics India Magazine (1.4M viewership)- https://analyticsindiamag.com/this-indian-has-cracked-multilingual-multimodal

Awards

Outstanding reviewer award (51/4450) for ACL 2023.
Young achiever award 2023 by Indian Achievers' Forum.
Best student paper award at ECIR 2023.
National Award for Outstanding Researcher 2022-23. (1/4500) by International Institute of Organized Research.
ACM grant to attend ACM Multimedia 2022 conference.
Samsung Citizen Award 2019, 2020 (Research) (4/9000).

Service

Conference Reviewer: AMLC 2023, NeurIPS 2023, BMVC 2023, CoLLA 2023, ACL 2023, CVPR 2023, EACL 2023, ACL 2022, ACL 2021, ICON 2020.
Journal Reviewer: Machine Learning, TMLR, Computer Speech & Language, ACL ARR.
Workshop Reviewer: ICLR - MoFo 2023, ICLR - MRL 2023, SocialNLP

Peer Reviewed Publications

	A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System Mauajama Firdaus, Avinash Madasu, Asif Ekbal Journal of Multimedia Tools and Applications [Paper] [Code]
	Is Multimodal Vision Supervision Beneficial to Language? Avinash Madasu, Vasudev Lal CVPR 2023 (NFVLR Workshop) [Paper] [Code]
	A Unified Framework for Emotion Identification and Generation in Dialogues Avinash Madasu, Mauajama Firdaus, Asif Ekbal EACL 2023 (SRW Workshop) [Paper]
	Improving video retrieval using multilingual knowledge transfer Avinash Madasu, Estelle Aflalo, Gabriela Ben Melech Stan, Shao-Yen Tseng, Gedas Bertasius, Vasudev Lal ECIR 2023 [Paper]
	What do Large Language Models Learn beyond Language? Avinash Madasu, Shashank Srivastava EMNLP 2022 (Findings) [Paper] [Code]
	Learning to Retrieve Videos by Asking Questions Avinash Madasu, Junier Oliva, Gedas Bertasius ACM Multimedia 2022 [Paper] [Code] [Poster]
	Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis Avinash Madasu, Vijjini Anvesh Rao ICPR 2020 [Paper]
	A Position Aware Decay Weighted Network for Aspect based Sentiment Analysis Avinash Madasu, Vijjini Anvesh Rao NLDB 2020 [Paper]
	Sequential Learning of Convolutional Features for Effective Text Classification Avinash Madasu, Vijjini Anvesh Rao EMNLP 2019 [Paper]
	Efficient Feature Selection techniques for Sentiment Analysis Avinash Madasu, Sivasankar E Journal of Multimedia Tools and Applications [Paper]
	Gated Convolutional Neural Networks for Domain Adaptation Avinash Madasu, Vijjini Anvesh Rao NLDB 2019 [Paper]
	Effectiveness of Self Normalizing Neural Networks for Text Classification Avinash Madasu, Vijjini Anvesh Rao CICLing 2019 [Paper]
	A Study of Feature Extraction techniques for Sentiment Analysis Avinash Madasu, Sivasankar E IEMIS 2018 [Paper]

Design taken from here