Eric Zelikman

Iā€™m a current Stanford CS PhD student (and Symbolic Systems graduate) fascinated by how (and whether) algorithms can learn meaningful representations and reason, advised by Nick Haber and Noah Goodman. Perhaps the most daunting exciting gap between biological and machine learning is the ease with which we learn to create and apply concepts about our world from experience: not only do we need much less experience to construct these concepts, but our understanding is flexible in novel situations, robust to slight changes, and generally disentangled.

Ultimately, I hope machine learning can teach us about non-machine learning and help us overcome the challenges facing humanity.

Also, I love baking bread, cooking, and exploring nature!

Selected Works

  1. 2023
    Parsel šŸ: A (De-)compositional Framework for Algorithmic Reasoning with Language Models
    Eric Zelikman, Qian Huang, Gabriel Poesia, Noah D. Goodman, Nick Haber,
    2023
  2. NeurIPS 2022
    STaR: Bootstrapping Reasoning With Reasoning
    Eric Zelikman*, Yuhuai (Tony) Wu*, Noah D. Goodman,
    NeurIPS 2022
  3. EMNLP 2022
    Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics
    Elisa Kreiss, Cynthia Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts,
    EMNLP 2022
  4. ICLR 2021
    Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
    Sharon Zhou, Eric Zelikman, Fred Lu, Andrew Y Ng, Gunnar Carlsson, Stefano Ermon,
    International Conference on Learning Representations 2021
  5. ICML Workshop
    CRUDE: Calibrating Regression Uncertainty Distributions Empirically
    Eric Zelikman, Christopher Healy, Sharon Zhou, Anand Avati,
    ICML Workshop on Uncertainty & Robustness in Deep Learning 2020
  6. NeurIPS Workshop
    Short-Term Solar Irradiance Forecasting Using Calibrated Probabilistic Models
    Eric Zelikman*, Sharon Zhou*, Jeremy Irvin*, Cooper Raterink, Hao Sheng, Jack Kelly, Ram Rajagopal, Andrew Y Ng, David Gagne,
    NeurIPS Workshop on Tackling Climate Change with Machine Learning 2020
  7. CVPR Workshop
    Transferable Adversarial Attacks on Deep Reinforcement Learning
    Xinlei Pan, Yulong Cao, Xindi Wu, Eric Zelikman, Chaowei Xiao, Yanan Sui, Rudrasis Chakraborty, Ronald S. Fearing,
    Short Paper in CVPR Workshop on Adversarial Machine Learning in Computer Vision 2020
  8. Honors Thesis
    Learning is its Own Reward: Exploring Worlds with Curiosity-driven Spiking Neural Networks
    Eric Zelikman (advised by Nick Haber),
    Undergraduate Honors Thesis 2020
  9. Contextual Salience for Fast and Accurate Sentence Vectors
    Eric Zelikman, Richard Socher,
    arXiv 2018

Education

Stanford University
Doctoral Student
Computer Science
September 2021 - Present
Stanford University
Bachelor of Science
Symbolic Systems with Honors
September 2016 - June 2020

Industry

Student Researcher Blueshift @ X & Google Research June 2022 ā€“ September 2022
Deep Learning Engineer Lazard July 2020 ā€“ September 2021
GANs Curriculum Developer DeepLearning.AI June ā€“ October 2020
Machine Learning Intern Argo AI June ā€“ September 2019
Machine Learning Intern Uncountable June ā€“ September 2018
& April ā€“ June 2019
Software Engineer Philometrics October 2016 ā€“ July 2017

Other

Reviewer Highlighted (8%) @ ICLR 2022, NeurIPS 2022, COLING 2022, EMNLP 2022 2022
Editor and 2019 Editor-in-Chief Stanford Undergraduate Research Journal 2016 ā€“ 2020
Teacher Stanford Splash 2016 - 2020
Section Leader Stanford Code in Place April - May 2020
TreeHacks, HopHacks, Cal Hacks, etc. Hackathons 2016 - 2020
Cofounder - Machine Learning Lead DeepDesigns.ai (defunct) January - July 2020
Awards NeurIPS 2022 Scholar Award; HopHacks 2019 2nd Overall; TreeHacks 2018 Energy Grand Prize; HopHacks 2017 1st Overall; 2022