Anastasia's profile photo
​Hi, I'm Anastasia πŸ‡ΊπŸ‡¦ πŸ‡¨πŸ‡¦! I am a PhD student at the University of Toronto and Vector Institute. I am fortunate to be working with Brenda Andrews and Jimmy Ba. I work closely with Mike Lewis and Amjad Almahairi. My research focus is natural language processing, foundation models and application of these areas to biomedical ML. I was fortunate to work with many amazing researchers through my internships at Meta (Facebook) AI , Microsoft Research , Amazon, and Recursion Pharmaceuticals. More details in my CV.
​​​​​​​​​​​​​​​​​​​​​​​​​​​​​

Research

I am interested in developing robust algorithms that can succeed in solving tasks in "real-world" setting, including learning under limited labels, data distribution shift and on multiple tasks. The key topics I am currently focusing on are: Some of my works:

Progressive Prompts
Progressive Prompts: continual learning for language models
A Razdaibiedina, Y Mao, R Hou, M Khabsa, M Lewis, A Almahairi
ICLR 2023
PaperCode


Residual Prompts
Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization
A Razdaibiedina, Y Mao, R Hou, M Khabsa, M Lewis, J Ba, A Almahairi
ACL 2023, Findings
PaperCode


REPINA illustration
Representation Projection Invariance Mitigates Representation Collapse
A Razdaibiedina, Z Karnin, A Khetan, D Khashabi, V Kapoor, V Madan
EMNLP 2023, Findings
Paper  Code (to be released soon!)  


Miread illustration
MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents
A Razdaibiedina, A Brechalov
ACL 2023
PaperCode


PIFiA illustration
PIFiA: a self-supervised method for protein functional annotation from single-cell imaging data
A Razdaibiedina, A Brechalov, H Friesen, M Mattiazzi-Usaj, HG Suresh, K Wang, C Boone, J Ba, B Andrews
In submission to Nature Methods
PaperCode


ICLR 2022 MLDD paper
Learning multi-scale functional representations of proteins from single-cell microscopy data
A Razdaibiedina, A Brechalov
ICLR 2022, MLDD
PaperCodePoster


CONCORT illustration
Multi-defect microscopy image restoration under limited data conditions
A Razdaibiedina, J Velayutham, M Modi
NeurIPS 2019, Medical Imaging workshop (rated in top-15 submissions)
PaperCodePoster

Experience

Talks

Teaching

I had wonderful opportunities to teach several ML courses at University of Toronto and Vector Institute:

Selected Honors & Awards

Contact

I am happy to get in touch! Please contact me at anastasia.razdaibiedina [at] mail.utoronto.ca or connect on LinkedIn.