Alexander Lew — accepted AI-conference papers

2026

From Tool to Teammate: Balancing Task-Oriented and Social Talk During Human-Robot Collaboration

Chayan Sarkar, Rebecca Ramnauth, Kate Candon, Alexander Lew, Marynel Vázquez

RA-L 2026

As robots become more integrated into shared work environments, effective communication must balance clear task directives with social engagement to support both efficiency and user satisfaction. This letter examines how people perceive task-oriented versus social dialogue during human–robot collabo

Cited by 0 Source ↗Scholar ↗

2021

PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming

Alexander Lew, Monica Agrawal, David Sontag, Vikash Mansinghka

AISTATS 2021poster

Data cleaning is naturally framed as probabilistic inference in a generative model of ground-truth data and likely errors, but the diversity of real-world error patterns and the hardness of inference make Bayesian approaches difficult to automate. We present PClean, a probabilistic programming langu…

Cited by 32 Source ↗PDF ↗code ↗Scholar ↗