**Darshan Thaker**

Latest

• PaCE: Parsimonious Concept Engineering for Large Language Models
• A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions
• Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
• Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
• Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning
• Understanding the Convergence of Adversarial Training for Overparameterized Linear Neural Networks
• Generating Synthetic Question-Answer Pairs for Transfer Learning in Biomedical Question Answering