about
Zizhao Hu

Zizhao Hu

Los Angeles

CS PhD @ USC · GLAMOR Lab

advised by Jesse Thomason & Mohammad Rostami @ Amazon

CVscholar

“Context is the new weight.”

I'm a researcher and engineer on Agentic AI. I work on agentic memory and AI alignment.

I earned my BS in Physics at Georgia Tech and am now a CS PhD at USC.

I'm conducting LLM unlearning research for the US Government's IARPA. Previously I was an ML domain lead at Handshake AI and a data engineer at Scale AI, where I collaborated with teams from OpenAI, Meta, and Anthropic to improve their unreleased black-box models.

what i work on
memory

Agentic Memory

Continual learning of AI agents — in-context learning, continual fine-tuning, unlearning, and in-context world models that adapt to evolving environments.

alignment

AI Alignment

Keeping capable models safe and under human control — post-training guardrails, multi-agent interaction risks, and AI behavioral study.

news & media
The RegisterQbitAITencent News36KrXYahoo TechAIToday
my path
  1. 2016

    Physics

    photonics & metasurface design · dynamic systems

  2. 2018

    Agile Systems

    bio-inspired flight, sensing, and locomotion

  3. 2021

    Robotics · RL

    policy learning for physical control and agent behavior

  4. 2022

    Continual Learning · VAE

    regularization design for variational autoencoders

  5. 2023

    Multimodal Generation

    diffusion models · vision-language model architecture

  6. 2026

    Agentic Memory

    in-context learning, continual fine-tuning, unlearning, and memory scaffolds; multi-agent coordination and predictive world models — adapting agents at the context, model, and population level

collaborators
Georgia TechUSCHandshake AIOpenAIMetaGoogle CloudScale AI
contact
linkedingithubemail