Shyam Upadhyay | श्याम उपाध्याय
🗣 /ʃjɑːm ʊ.pɑːd̪ʱ.jɑːj/ , He/Him
I am a Staff Research Scientist at Google.
I work on improving the core model quality of Gemini, with a special focus on improving its instruction following abilities (see blog post from a recent launch). Prior to this, I helped develop features that allowed users to have more natural conversations with the Google Assistant.
Previously, I completed my Ph.D. at the University of Pennsylvania, under the guidance of Prof. Dan Roth. Even before that, I obtained an undergraduate degree in Computer Science and Engineering from the Indian Institute of Technology at Kanpur.
Selected Publications
-
EACL 2023Efficient Encoders for Streaming Sequence TaggingIn EACL 2023
-
StarSEM 2023Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions?In StarSEM 2023
-
Interspeech 2022Streaming Intended Query Detection using E2E Modeling for Continued ConversationIn Interspeech 2022
-
ACL 2022TableFormer: Robust Transformer Modeling for Table-Text EncodingIn ACL 2022
-
ACL 2021TIMEDIAL: Temporal Commonsense Reasoning in DialogIn ACL 2021
-
EMNLP 2018Joint Multilingual Supervision for Cross-lingual Entity LinkingIn EMNLP 2018
-
NAACL 2018Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple SentencesIn NAACL 2018
-
ICASSP 2018(Almost) Zero-Shot Cross-Lingual Spoken Language UnderstandingIn ICASSP 2018
-
EMNLP 2016Learning from Explicit and Implicit Supervision Jointly For Algebra Word ProblemsIn EMNLP 2016
-
ACL 2016Cross-lingual Models of Word Embeddings: An Empirical ComparisonIn ACL 2016