Alex Aiken

Optimizing Mixture of Experts using Dynamic Recompilations

2022 · arXiv (Cornell University)

The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data flow in Mixture of …

Prolego: Time-Series Analysis for Predicting Failures in Complex Systems

2023

Failures in large, complex systems can be difficult to diagnose and expensive for both the system maintainers and users. We present techniques for predicting failures when there is sparse ground truth in sensor logs and …

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

2025 · arXiv (Cornell University)

Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural language, their ability …