Baharan Mirzasoleiman

6

Papers

15

Total Citations

Papers (6)

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions

NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction

Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks