Amir Yazdanbakhsh

The paper introduces AlphaEvolve, an evolutionary search framework that automates the optimization of Fully Homomorphic Encryption (FHE) kernels on TPUs, achieving significant speedups over human-engineered baselines.

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughput under strict latency constraints.

AI-PROPELLER introduces a novel interprocedural code layout optimization system that uses an agentic evolutionary workflow to achieve significant, measurable performance gains in large-scale, real-world binaries.