Kaiya Ivy Zhao

Kaiya Ivy Zhao

EECS PhD Student @ MIT

Massachusetts Institute of Technology

kyzhao@mit.edu

Biography

Hi! I’m Ivy, a PhD student at MIT CSAIL where I am fortunate to be co-advised by Professor Phillip Isola and Professor Josh Tenenbaum. Previously, I had a wonderful experience working with Professor Guangyu Robert Yang at MIT on autonomous agents with real-time interaction.

My research interest lies in the intersection of AI and human intelligence, with a focus on AI that can simulate human-like intelligence and cognition. Something on my mind these days:

  • World Model & Embodied Intelligence: Inspired by fabulous mental simulation capabilities in humans, I’m interested in how intelligent agents form good understandings of the world that support prediction, counterfactual reasoning, generalization and adaptation.
  • Agentic System in Interactive Environment: I am interested in agentic systems that learn through interaction with an emphasis on long-horizon decision-making and autonomous behavior. I often use games as compact, controllable environments relevant to real-world deployment.
  • Cognitive Science & Social Reasoning: How can insights from human cognition inform the design of human-like agents? I’m curious about the computational foundations of Theory-of-Mind to build AI agents that collaborate naturally with us.

I publish under the name “Kaiya Ivy Zhao”, where “Zhao” is my surname and “Kaiya” is the forename. “Ivy”(ai·vee) is the name I usually go by.

Outside the research, my world is filled with the vibrancy of musicals, the thrill of snowboarding, the companionship of cats and the wonder of travel. Each of these hobbies offers me a unique perspective on life and creativity.

Feel free to reach out via email to discuss research, collaborations, or schedule a chat!

Interests
  • Embodied Intelligence
  • Representation Learning
  • Agents and Agentic AI
  • Cognitive Science
Education
  • PhD in Computer Science, 2024 - present

    Massachusetts Institute of Technology

  • BSc in Computer Science, 2020 - 2024

    Fudan University

Recent Publications

Quickly discover relevant content by filtering publications.
(2026). AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games.

Cite arXiv

(2025). HugAgent: Benchmarking LLMs for Simulation of Individualized Human Reasoning. Language, Agent, and World Models Workshop @ NeurIPS 2025 (Spotlight).

Cite arXiv

(2025). Assessing Adaptive World Models in Machines with Novel Games. Language, Agent, and World Models Workshop @ NeurIPS 2025 (Best Paper Award).

Cite arXiv

(2025). Simulating Society Requires Simulating Thought. NeurIPS 2025 Position Paper.

Cite arXiv

(2025). Cross-Modal Alignment Regularization: Enhancing Language Models with Vision Model Representations. Representational Alignment (Re-Align) Workshop @ ICLR 2025.

Cite URL

Contact

Feel free to get in touch with me using the contact options below.