Publications

• Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters-Adarsh Kumar, Kausik Subramanian, Shivaram Venkataraman, Aditya Akella, DistributedML@CoNEXT2021

• Accelerating Deep Learning Inference via Learned Cache-Adarsh Kumar*, Arjun Balasubramanian*, Yuhan Liu, Han Cao, Shivaram Venkataraman, Aditya Akella, under submission

• Can Adversarial Weight Perturbations Inject Neural Backdoors?-Adarsh Kumar, Siddhant Garg, Vibhor Goel, Yingyu Liang, CIKM 2020

• MADST- Multi Attention Based Scalable Dialog State Tracking-Adarsh Kumar, Peter Ku, Anuj Goyal, Angeliki Metallinou, Dilek H. Tur, AAAI 2020, NeuRIPS Conversational AI Workshop 2019

• MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines-Mihail Eric, Rahul Goel, Shachi Paul, Adarsh Kumar, Abhishek Sethi, Peter Ku, Anuj Goyal, Shuyang Gao, Dilek H. Tur, LREC 2020

• Accelerating deep learning inference via freezing- Adarsh Kumar, Arjun Balasubramanian, Shivaram Venkataraman, Aditya Akella, HotCloud 2019

• Translating Web Search Queries into Natural Language Questions- Adarsh Kumar, Sandipan Dandapat, Sushil Chordia, LREC 2018

Patents

• Predicting brand personality using textual content- Anandhavelu Natarajan, Niyati Himanshu Chhaya, R Sundararajan, Pradyot Prakash, Adarsh Kumar, Niloy Ganguly USPTO