Balakrishnan Varadarajan

Researcher, Reality labs, Meta

Joined

February 2019

Names

Balakrishnan Varadarajan (Preferred)

Emails

****@gmail.com (Confirmed)

****@waymo.com (Confirmed)

****@meta.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Researcher

Reality labs, Meta (meta.com)

2022 – 2050

Researcher

Google (google.com)

2019 – 2022

software

Google (google.com)

2011 – 2019

PhD student

Google, Johns Hopkins University (jhu.edu)

2006 – 2011

Advisors, Relations & Conflicts

Coauthor

Balakrishnan Varadarajan

2008 – 2016

Coauthor

Trac Tran

2011 – 2014

PhD Advisor

Sanjeev Khudanpur

2006 – 2011

Expertise

Computer vision

Present

Autonomous driving

2006 – 2023

Deep learning

2006 – 2023

Computer Vision

2006 – 2023

Publications

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao, Lemeng Wu, Jun Chen, Chenchen Zhu, Zechun Liu, Fanyi Xiao, Balakrishnan Varadarajan, Florian Bordes, Zhuang Liu, Hu Xu, Hyunwoo J. Kim, Bilge Soran, Raghuraman Krishnamoorthi, Mohamed Elhoseiny, Vikas Chandra
- ICML 2025 poster
- Readers: Everyone
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao, Lemeng Wu, Jun Chen, Chenchen Zhu, Zechun Liu, Fanyi Xiao, Balakrishnan Varadarajan, Florian Bordes, Zhuang Liu, Hu Xu, Bilge Soran, Raghuraman Krishnamoorthi, Mohamed Elhoseiny, Vikas Chandra
- Submitted to ICLR 2025
- Readers: Everyone
Large-Scale Training Framework for Video Annotation.
Seong Jae Hwang, Joonseok Lee, Balakrishnan Varadarajan, Ariel Gordon, Zheng Xu, Apostol Natsev
- 2019 (modified: 13 May 2020)
- KDD2019
- Readers: Everyone
Collaborative Deep Metric Learning for Video Understanding
Joonseok Lee, Sami Abu-El-Haija, Balakrishnan Varadarajan, Apostol Natsev
- 2018 (modified: 16 Jul 2019)
- KDD 2018
- Readers: Everyone
Exploring the Relative Role of Bottom-up and Top-down Information in Phoneme Learning
Abdellah Fourtassi, Thomas Schatz, Balakrishnan Varadarajan, Emmanuel Dupoux
- 2014 (modified: 16 Jul 2019)
- ACL (2) 2014
- Readers: Everyone
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition.
Aren Jansen, Emmanuel Dupoux, Sharon Goldwater, Mark Johnson, Sanjeev Khudanpur, Kenneth Church, Naomi Feldman, Hynek Hermansky, Florian Metze, Richard C. Rose, Mike Seltzer, Pascal Clark, Ian McGraw, Balakrishnan Varadarajan, Erin Bennett, Benjamin Börschinger, Justin Chiu, Ewan Dunbar, Abdellah Fourtassi, David Harwath et al. (7 additional authors not shown)
- 2013 (modified: 09 Nov 2022)
- ICASSP2013
- Readers: Everyone
Learning and inference algorithms for partially observed structured switching vector autoregressive models.
Balakrishnan Varadarajan, Sanjeev Khudanpur
- 2011 (modified: 09 Nov 2022)
- ICASSP2011
- Readers: Everyone
Stepwise Optimal Subspace Pursuit for Improving Sparse Recovery.
Balakrishnan Varadarajan, Sanjeev Khudanpur, Trac D. Tran
- 2011 (modified: 09 Nov 2022)
- IEEE Signal Process. Lett.2011
- Readers: Everyone
Dirichlet Mixture Models of neural net posteriors for HMM-based speech recognition.
Balakrishnan Varadarajan, Garimella S. V. S. Sivaram, Sanjeev Khudanpur
- 2011 (modified: 09 Nov 2022)
- ICASSP2011
- Readers: Everyone
Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion.
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex Acero
- 2010 (modified: 13 May 2020)
- Comput. Speech Lang.2010
- Readers: Everyone

View all 19 publications

Co-Authors

View all 62 co-authors