Zenna Tavares bio photo

Zenna Tavares

I'm an researcher at Columbia University, formerly at MIT. I think about how to build computer programs that think as humans think. You can contact me on zt2297[at]columbia[dot]edu

Email Twitter Github

Publications

Under Preparation

  • The Random Conditional Distribution - preprint
  • Synthesis of Singular Causal Explanations
  • Machine Reasoning: Insights From the Copernican Revolution

Publications

  • Combining Functional and Automata Synthesis to Discover Causal Reactive Programs - Ria Das, Joshua B. Tenenbaum, Armando Solar-Lezama, Zenna Tavares - under submission

  • MetaCOG: Learning a metacognition to recover what objects are actually there - Marlene Berke, Zhangir Azerbayev, Mario Belledonne, Zenna Tavares, Julian Jara-Ettinger - under submission

  • A Language for Counterfactual Generative Models - Zenna Tavares, James Koppel, Xin Zhang, Ria Das, Armando Solar-Lezama - ICML 2021

  • Synthesizing Programmatic Policies that Inductively Generalize - Jeevana Priya Inala, Osbert Bastani, Zenna Tavares, Armando Solar-Lezama - ICLR 2020 pdf

  • Predicate Exchange: Inference with Declarative Knowledge - Zenna, Tavares, Javier Burroni, Edgar, Minasyan, Armando Solar-Lezama, Rajesh Ranganath - ICML 2019 pdf

  • Adversarial Inversion for Amortized Inference - Zenna Tavares, Edgar Minasyan, Armando Solar-Lezama - ICML 2017, Implicit Models Workshop pdf

  • Smooth Nondeterministic Arrows - Zenna Tavares, Armando Solar-Lezama - NIPS 2015, Black-Box Inference Workshop (Best Paper) pdf

  • Parametric Inverse Simulation - Zenna Tavares, Armando Solar-Lezama - NIPS 2016, Advances in Approximate Bayesian Inference

  • Learning Distribution Sensitive Data Structures - Zenna Tavares, Armando Solar-Lezama - AAAI Spring Symposium 2017

  • Probabilistic Programming by Abstraction Refinement - Zenna Tavares, Armando Solar-Lezama - NIPS 2014, Probabilistic Programming Workshop