George Stoica

Fourth Year ML PhD Student @ Georgia Tech, Visiting @ UW.

CODA

756 West Peachtree St. North West

Atlanta, GA 30308

I am a fourth-year Machine Learning PhD Student in the School of Interactive Computing at Georgia Institute of Technology advised by Professor Judy Hoffman. I am also a visiting PhD student in the at the University of Washington, working with Professor Ranjay Krishna. I am very fortunate to be supported by the National Science Foundation Graduate Research Fellowship.

I am broadly interested in computer vision and natural language processing, with a focus on representation learning and understanding. I am particularly interested in topics involving large-scale models, multitask & continual learning, multimodality, transfer learning, efficiency, and architecture development.

Previously, I was a Research Assistant in the Machine Learning Department at Carnegie Mellon University advised by Professor Barnabás Póczos. I hold a Bachelors degree in Statistics and Machine Learning from Carnegie Mellon University with School of Computer Science and University Honors.

News

Oct 25, 2024 Model merging with SVD to tie the Knots released on arXiv 2024
Sept 6, 2024 Started visiting PhD studentship at UW, under Professor Ranjay Krishna
Jan 15, 2024 Our V2 of ZipIt! Merging Models from Different Tasks without Training was accepted to ICLR 2024
May 4, 2023 Our V1 of ZipIt! Merging Models from Different Tasks without Training was released on arXiv
March 30, 2023 I was very fortunate to be awarded the NSF Graduate Research Fellowship
December 9, 2022 Bi-Directional Self-Attention for Vision Transformers won the best paper award at the NeurIPS 2022 VTTA Workshop
Dec 2, 2020 Our new relation extraction dataset Re-TACRED was accepted to AAAI 2021
Oct 30, 2020 Our new relation extraction dataset Re-TACRED was accepted at the NeurIPS 2020 KR2ML Worshop
Oct 30, 2020 Our work on cyclically combining Knowledge Graphs and Relation Extraction was accepted at the NeurIPS 2020 KR2ML Workshop.
Dec 10, 2019 Our work on Knowledge Graph Link Prediction was accepted to AAAI 2020