CV

This is a short version of my resume. For a full list of publications, check out my Google Scholar page.

Education

• Ph.D in Computer Science, University of Washington, 2022
  • Thesis: How to train your self-supervised NLP model: Investigating pre-training objectives, data, and scale.
  • Advisers: Luke Zettlemoyer and Dan Weld
• Master of Technology in Computer Science, IIT Bombay, 2014
• Bachelor of Technology in Computer Science, VNIT Nagpur, 2012

Employment

• Research Scientist, Google DeepMind (May 2022 - Present)
• Visiting Researcher, Meta AI Research (formerly FAIR) (April 2020 - March 2022})
• Software Engineer, IBM Research (August 2014 - May 2015)
• Internships: Google (Summer 2019), AI2 (Fall 2017)

Representative Publications

• Gemini Team, Google. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. ArXiv 2507.06261, 2025.

• Peter Shaw, Mandar Joshi, James Cohan, Jonathan Berant, Panupong Pasupat, Hexiang Hu, Urvashi Khandelwal, Kenton Lee, Kristina Toutanova. From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces. NeurIPS 2023. * equal contribution

• Google AI Team. PaLI-X: On Scaling up a Multilingual Vision and Language Model. ArXiv 2305.18565, 2023.

• Kenton Lee*, Mandar Joshi*, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, Kristina Toutanova. Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding. ArXiv 2210.03347, 2022.
  * equal contribution

• Armen Aghajanyan, Bernie Huang, Candace Ross, Vladimir Karpukhin, Hu Xu, Naman Goyal, Dmytro Okhonko, Mandar Joshi, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer. CM3: A Causal Masked Multimodal Model of the Internet . ArXiv 2201.07520, 2022.

• Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov. RoBERTa: A Robustly Optimized BERT Pretraining Approach . ArXiv:1907.11692, 2019. [ code ]

• Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, Omer Levy. SpanBERT: Improving Pre-training by Representing and Predicting Spans. TACL, 2019. Equal Contribution [ code ]
  * equal contribution

• Mandar Joshi, Eunsol Choi, Daniel Weld, Luke Zettlemoyer. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension. Association for Computational Linguistics (ACL) 2017. [ website ] [ bib ]

Misc

• Invited talk on “Efficient Scalable Pre-training for Natural Language Processing” at KDD 2020 Deep Learning Day.
• Awarded Microsoft Endowment Fellowship for the academic year 2015-2016.
• All India Rank 2 in GATE (Graduate Aptitude Test in Engineering) 2012 amongst 150,000 applicants. The test is conducted by IITs for admission into their graduate programs. Service and Courses.