معرفی
Kevin Ellis is an Assistant Professor in the Department of Computer Science at Cornell University, affiliated with the College of Engineering. His research focuses on program synthesis, cognitive science, and neurosymbolic AI. He teaches courses such as Foundations of AI: Reasoning and Decision-Making (CS3700) and Program Synthesis (CS6172). Ellis has advised multiple PhD and master's students, including Hao Tang, Simon Alford, and Wen-Ding Li (now at Mistral). His work has been recognized with the Best Paper award at the ARCPrize 2025. Ellis's research spans applications in robotics, quantum computing, and human-like learning, often leveraging Bayesian methods and large language models. He leads teams exploring the intersection of neural networks and symbolic systems through projects like WorldCoder and DreamCoder.
- Education: PhD in Computer Science from MIT (advisor: Joshua B. Tenenbaum).
Research interests include neurosymbolic integration, program induction, and cognitive modeling. His recent work emphasizes scalable synthesis techniques, probabilistic reasoning, and human-AI collaboration. Ellis's lab develops tools for automated program generation and interpretable AI systems. He actively contributes to open-source projects (e.g., GitHub repositories) and collaborates internationally on NSF-funded initiatives like the CAREER award for Symbolic Learning with LLMs.
