papers

• Driving and suppressing the human language network using large language models (20 Jan 2024)
  Generating sentences that control language system activations in the human brain
• Understanding Computer Programs - Computational and Cognitive Perspectives (20 Apr 2023)
  My PhD thesis
• AutoAcademic (07 Apr 2023)
  Get two LLMs to generate a paper that will be accepted at a conference of your choice
• RaceInjector - Injecting Races To Evaluate And Learn Dynamic Race Detection Algorithms (20 Mar 2023)
  Evaluating race detection algorithms proposed over the last four decades
• GOLI - Goal-Optimized Linguistic Stimuli for Psycholinguistics and Cognitive Neuroscience (30 Jan 2023)
  Automated generation of psycholinguistic stimuli
• Convergent representations of computer programs in human and artificial neural networks (01 Oct 2022)
  What aspects of computer programs are represented in the human brain during program comprehension?
• CLAWSAT - Towards both robust and accurate code models (10 Jan 2022)
  Can adversarial codes be used to improve the generalization and robustness of pre-trained code models? Yes.
• Can cognitive neuroscience inform neuro-symbolic models? (20 Jul 2021)
  Can recent studies which improve our understanding of how the human brain is involved in processing language possibly help inform neural-symbolic language models?
• Generating adversarial programs (12 Jan 2021)
  A differentiable generator of adversarial computer programs which can deceive ML models trained on computer programs
• Comprehension of computer code relies primarily on domain-general executive brain regions (15 Dec 2020)
  Which parts of our brains light up when reading programs? Is it the language region? Are programs treated as natural languages by the brain? Turns out, no.
• Dependency-based neural representations for classifying lines of programs (15 Feb 2020)
  How can ML models be used to represent lines of programs? We design a dependency-graph based neural representation of programs, which evaluates whether a given line of code has a vulnerability in it or not.
• Human Baseline for Zero-Shot Transfer Learning of Good Dogs (07 Apr 2019)
  How good are humans at zero-shot identification of dogs?
• On the application of Danskin's to derivative-free minimax problems (15 Jul 2018)
  We show how evolution strategies, which are stochastic gradient approximators, can be used to solve min-max problems.
• Data science for kids (07 Jul 2017)
  At Aspiring Minds, we also started a fun side project where we introduced concepts in data science to high school students. It was a great deal of fun putting together fun exercises and a lesson plan. Check out our webpage datasciencekids.org for details!
• Evaluating human skills using machine learning (15 Jul 2016)
  At Aspiring Minds, we showed how the problem of quantifying human skills can be cast as a problem in machine learning. Our CACM paper provides details on this framework, while our KDD works show how we evaluate computer programs using ML.