Pushkar Mishra
Pushkar Mishra is a Lead AI researcher at Google DeepMind. His research interests include Generative AI, Core Machine Learning, and Natural Language Processing.
Before Google DeepMind, he was at Meta AI (ex-Facebook AI), where he led the company-wide effort on robust recommender systems and contributed to the pivotal initiative on open-source foundation models as one of the authors of Llama 2.
Research Areas
Latest Updates
New paper on modelling human variations in rating tasks using interpretable and steerable natural language descriptions of underlying values compressed from in-context demonstrations
Value Profiles for Encoding Human Variation
Taylor Sorensen, Pushkar Mishra, Roma Patel, Michael Henry Tessler, Michiel Bakker, Georgina Evans, Iason Gabriel, Noah Goodman, Verena Rieser
New paper on metrics for quantifying how different rater groups respond to the severity of safety violations in generative outputs
Nuanced Safety in Generative AI: How Demographics Shape Responsiveness to Severity
Pushkar Mishra, Charvi Rastogi, Stephen R. Pfohl, Alicia Parrish, Roma Patel, Mark Diaz, Ding Wang, Michela Paganini, Vinodkumar Prabhakaran, Lora Aroyo, Verena Rieser
New paper on gathering insights into safety from diverse rater groups at the NeurIPS 2024 Safe Generative AI workshop
Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
Charvi Rastogi, Tian Huey Teh, Pushkar Mishra, Roma Patel, Zoe Ashwood, Aida Mostafazadeh Davani, Mark Diaz, Michela Paganini, Alicia Parrish, Ding Wang, Vinodkumar Prabhakaran, Lora Aroyo, Verena Rieser