Robert Wu (吴才铨)

University of Toronto (UofT)
Email: rupert[at]cs.toronto.edu (research), rupert.wu[at]utoronto.ca (teaching)
Links: { github, gitlab, linkedin, scholar, }

[about] [projects] [cv]


About Me

I’m a junior researcher and MSc student at the University of Toronto (UofT) advised by Prof. Vardan Papyan. I am generally interested in deep learning (recently language modeling and representation learning) and computer systems (compilers and parallel programming). I completed my BSc also at UofT (Victoria College) and interned recently at AWS and Cohere. Toronto has been home my whole life but I’m still exploring its hidden gems.

Affiliations: MLC (community), C4AI (community), AutoMLG@UTMIST.


Publications & Pre-Prints | [All Projects]

  1. Linguistic Collapse: Neural Collapse in (Large) Language Models
    Robert Wu, Vardan Papyan
    [arxiv] [code]
  2. Towards One Shot Search Space Poisoning in Neural Architecture Search
    Nayan Saxena, Robert Wu, Rohan Jain
    Student Abstract+Poster @ AAAI 2022
    [proceedings] [poster] [arxiv] [code]
  3. NeuralArTS: Structuring Neural Architecture Search with Type Theory
    Robert Wu, Nayan Saxena, Rohan Jain
    Student Abstract+Poster @ AAAI 2022 (top 20, oral)
    [proceedings] [poster] [arxiv] [code]
  4. Poisoning the Search Space in Neural Architecture Search
    Robert Wu*, Nayan Saxena*, Rohan Jain*
    AdvML Workshop @ ICML 2021
    [openreview] [poster] [arxiv] [code]

(* equal contribution)


Teaching

As a Teaching Assistant