I am an AI Researcher with a background in pure and applied mathematics, scientific computing, and machine learning. My current research focuses on:
- Mechanistic Interpretability of Transformer Models
- Sparse and Efficient Neural Networks
- Operator Learning (FNO, Neural Operators)
- Foundation Models for Scientific and Physical Systems
- Mathematical Foundations of Modern AI
My work bridges theory and practice, combining:
- Optimization & information theory
- Sparse representation learning
- Probabilistic modeling
- Large-scale deep learning systems
- Alignment & interpretability of large language models
- Reasoning and representation in foundation models
- Efficient intelligence and sparse architectures
- Scientific discovery with AI
- Mechanistic Interpretability
- Sparse Neural Networks
- Neural Operators (FNO, PINNs)
- Scientific Machine Learning
- Probabilistic Modeling
- High-dimensional Optimization
- Mechanistic AI Interpretability (Activation Patching, Circuit Tracing)
- Learning Fourier Neural Operators
- Sparse Neural Networks with Learned Masks
- Kernel-based Operator Learning