about
Zizhao Hu

Zizhao Hu

Los Angeles

CS PhD @ USC · GLAMOR Lab · advised by Jesse Thomason

scholarlinkedingithubemail

Context is the new weight. Low-latency control of what to remember, forget, and explore decides next-gen world-model-aware, self-improving AI. I work on continual learning, unlearning, memory management, and task adaptation — at the agentic context (in-context RL, harness) and model level (distillation, finetuning).

what i work on
memory

Agentic Memory

Continual learning of AI agents — in-context learning, continual fine-tuning, and unlearning.

world model

World Model

In-context world models, adaptation to post-training task worlds, and adapting agents in evolving envs.

latency

Low-Latency AI

Efficient attention architectures, KV-cache compression, latent segmentation, and recurrent transformers.

safety

AI Safety

Synthetic data training, risks of multi-agent interaction, post-training guardrails, and AI behavioral study.

news & media
The RegisterQbitAITencent News36KrXYahoo TechAIToday
my path
  1. 01physics

    Physics

    photonics & metasurface design · dynamic systems

  2. 02biophysics

    Agile Systems · Animal Flight

    bio-inspired flight, sensing, and locomotion

  3. 03robotics

    Robotics · Reinforcement Learning

    policy learning for physical control and agent behavior

  4. 04vae

    Continual Learning · VAE

    regularization design for variational autoencoders

  5. 05multimodal

    Multimodal Generation

    diffusion models · vision-language model architecture

  6. 06continual · multi-agent

    Continual Learning · Multi-Agent

    coordination, division of labor, and mutual verification across agents — continual adaptation at the population level

  7. 07agentic-memorycurrent

    Agentic Memory

    in-context learning, continual fine-tuning, unlearning, and memory scaffolds — adapting agents at the context and model level

  8. 08horizon

    World Models · Low-Latency AI

    predictive world models and the architectures to serve them in real time

collaborators