Alborz Geramifard

Research Manager

I am a research manager at Facebook AI. Prior to joining Facebook, I led the conversational AI team at Amazon Alexa and led the creation of more than a dozen NLU Models. Prior to Amazon, I was a postdoctoral fellow at MIT’s Laboratory for Information & Decision Systems. I received my PhD from MIT in 2011 working with Jonathan How and Nicholas Roy on automated representation learning for reinforcement learning and safe exploration in sensitive MDPs. I did my MSc in University of Alberta under the supervision of Richard Sutton and Michael Bowling in 2008, where I worked on data efficient online reinforcement learning. I was the recipient of the NSERC postgraduate scholarships 2010-2012 program.


Conversational AI, reinforcement learning, natural language processing

Latest Publications

ACL - October 1, 2021

DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

Hung Le, Chinnadhurai Sankar, Seungwhan Moon, Ahmad Beirami, Alborz Geramifard, Satwik Kottur

SIGDIAL - August 1, 2021

Annotation Inconsistency and Entity Bias in MultiWOZ

Kun Qian, Ahmad Beirami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar

Uncertainty and Robustness in Deep Learning Workshop at ICML - June 24, 2021

DAIR: Data Augmented Invariant Regularization

Tianjian Huang, Chinnadhurai Sankar, Pooyan Amini, Satwik Kottur, Alborz Geramifard, Meisam Razaviyayn, Ahmad Beirami

COLING - December 8, 2020

Situated and Interactive Multimodal Conversations

Seungwhan Moon, Satwik Kottur, Paul A. Crook, Ankita De, Shivani Poddar, Theodore Levin, David Whitney, Daniel Difranco, Ahmad Beirami, Eunjoon Cho, Rajen Subba, Alborz Geramifard

COLING - December 8, 2020

Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming

Zhenpeng Zhou, Ahmad Beirami, Paul A. Crook, Pararth Shah, Rajen Subba, Alborz Geramifard