My name is Zhiyuan Song, but you can also call me Allen. I am currently an M.S. student in Computer and Information Science (AI Track) at the University of Pennsylvania. I am fortunate to work as a Research Assistant advised by Prof. Jiatao Gu, focusing on multimodal foundation models and large language model reasoning.

My primary research interests lie in building intelligent, real-time interactive systems. I actively explore audio-language modeling, reinforcement learning (RLVR/GRPO), and continuous Chain-of-Thought (CoT) reasoning for Omni-models. I am also passionate about robust AI infrastructure and optimizing distributed training pipelines.

I completed my undergraduate studies at the University of Virginia, where I double majored in Computer Science and Applied Statistics and graduated with High Distinction, and was fortunate to conduct research advised by Prof. Madhav Marathe, Prof. S.S. Ravi, and Prof. N. Rich Nguyen.

I welcome any entrepreneurial ideas and am always open to finding co-founders for exciting ventures. Feel free to reach out — I'd love to chat!

Education

News

• [May 2026]New preprint: "Learning When to Think While Listening in Large Audio-Language Models" is now on arXiv.
• [Jun 2026]I will be joining Millennium Management as an AI Engineer Intern!
• [Aug 2025]I started my M.S. in CIS at UPenn and joined Prof. Jiatao Gu's group as a Research Assistant.
• [Jul 2025]Led the team as Tech Lead & MLE at AdventureX Hackathon, building a full-duplex real-time audio AI assistant.
• [Dec 2024]Graduated from University of Virginia with High Distinction.
• [Aug 2024]Paper "SL4HOI" accepted at KDD 2024 in Barcelona.

Selected Publications