Publications

Bhavya Vasudeva, Deqing Fu, Tianyi Zhou, Elliott Kau, Youqi Huang, Vatsal Sharan (2024). Simplicity Bias of Transformers to Learn Low Sensitivity Functions. BGPT Workshop@ICLR'24; Under review.

Bhavya Vasudeva, Puneesh Deora, Christos Thrampoulidis (2024). Implicit Bias and Fast Convergence Rates for Self-attention. BGPT Workshop@ICLR'24; Under review.

Bhavya Vasudeva, Kameron Shahabi, Vatsal Sharan (2023). Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness. SCIS Workshop@ICML'23; Under review.

Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Umapada Pal, Sukalpa Chanda (2021). LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning. ICCV 2021.

Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Pyari Mohan Pradhan (2020). Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction. WACV 2022.