Anthony Song

✉ Email: abs343 [at] cornell [dot] edu

🐙 GitHub / 🎓 Google Scholar / 💼 LinkedIn / 📝 Blog

I am an undergraduate student at Cornell University, pursuing dual degrees in Electrical Engineering and Computer Science. I have interned at AMD, contributing to verification / diagnostics tools for AI Engine Compilers. Outside of academics, I am big fan of basketball, sketching, origami, photography, and cooking. I am also a big foodie so feel free to reach out to me if you have any recommendations!

I am fortunate to be advised by Prof. Zhiru Zhang in the Computer Systems Laboratory. Previously, I worked with Prof. Tapomayukh Bhattacharjee at EmPRISE Lab and Prof. Maja Matarić at the Interaction Lab.

My research focuses on building compilers, software systems, and hardware accelerators for efficient computation. I'm especially interested in hardware–software co-design: developing domain-specific languages, runtimes, and toolchains that enable productive programming of heterogeneous hardware through coordinated design across system layers. I’m excited to apply these ideas to machine learning, AI, and robotics, where end-to-end co-design can unlock major gains in performance and efficiency.

News

[06/25] FEAST won the RSS 2025 Outstanding Paper Award and is a finalist for the Outstanding Systems Paper Award!
[04/25] Our robotics systems paper FEAST has been accepted to RSS 2025.

Education

Cornell University

B.S. in Electrical Engineering & Computer Science

Aug 2023 – May 2027

Work Experience

Zhang Research Group — Cornell University

Research Assistant

Hardware Accelerators for Linear Transformations

Advisor: Zhiru Zhang

Aug 2024 – Present

Advanced Micro Devices

AI Software Engineer Intern

Automated Diagnostics Tools for AI Engine Compilers

Mentors: Keshav Gurushankar, Bin Tu

May 2025 – Aug 2025

EmPRISE Lab — Cornell University

Research Assistant

Robot Systems Design for Assisted Feeding

Advisor: Tapomayukh Bhattacharjee

Dec 2023 – May 2025

Interaction Lab — University of Southern California

Research Intern

Visual Simultaneous Localization and Mapping

Advisor: Maja Matarić

May 2024 – Aug 2024

Publications

FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization

Rajat Kumar Jenamani, Tom Silver, Ben Dodson, Shiqin Tong, Anthony Song, Yuting Yang, Ziang Liu, Benjamin Howe, Aimee Whitneck, Tapomayukh Bhattacharjee

RSS, 2025

(Best Paper Award, Best Systems Paper Finalist)

[abs] [project] [paper] [code]

Mealtime assistance is a critical activity of daily living (ADL) for individuals with motor impairments. Existing robotic systems typically require extensive customization and fine-tuning for each user, limiting their real-world deployment. We present FEAST, a flexible mealtime-assistance system that enables care recipients to personalize their feeding experience in-the-wild with minimal researcher intervention. FEAST incorporates adaptive learning mechanisms that allow the system to learn from user preferences and feedback across diverse in-home scenarios. Our system demonstrates significant improvements in user satisfaction and eating independence compared to traditional approaches, enabling more widespread adoption of assistive feeding technology.