Scholar
Bhavya Vasudeva
Google Scholar ID: ZCSsIokAAAAJ
University of Southern California
Machine Learning
Optimization
Robustness
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
270
H-index
8
i10-index
8
Publications
14
Co-authors
12
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
7 items
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
2026
Cited
0
How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
2025
Cited
0
In-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly
2025
Cited
0
Latent Concept Disentanglement in Transformer-based Language Models
2025
Cited
0
The Rich and the Simple: On the Implicit Bias of Adam and SGD
2025
Cited
0
Transformers Learn Low Sensitivity Functions: Investigations and Implications
2024
Cited
5
Implicit Bias and Fast Convergence Rates for Self-attention
arXiv.org · 2024
Cited
9
Co-authors
10 total
Puneesh Deora
University of British Columbia
Saumik Bhattacharya
IIT Kharagpur, India
Vatsal Sharan
Stanford University
Christos Thrampoulidis
Assistant Professor, University of British Columbia, ECE Department
Deqing Fu
USC
Mahdi Soltanolkotabi
University of Southern California
Cyrus Rashtchian
Google Research
Rina Panigrahy
Research Scientist, Google Inc.
