Skip to content

hey, i'm will.

I study math & CS at the University of Chicago. I'm an AI Risk Fellow at XLab and I'm building Caisson AI, offline AI assistants for field technicians. Previously, I researched LLM watermark detection at MIT Lincoln Laboratory.

GitHubLinkedInEmail
chicago, il

research

IEEE International Conference on Data Mining (ICDM) 2025 · Best Paper Award

Signature vs. Substance: Evaluating the Balance of Adversarial Resistance and Linguistic Quality in Watermarking Large Language Models

William Guo, Adaku Uchendu, Ana Smith

How well do LLM watermarks survive paraphrase and back-translation attacks, and what do they cost in linguistic quality? A systematic evaluation across watermarking schemes, from work at MIT Lincoln Laboratory.

arXivPoster

experience

  • X

    XLab

    AI Risk Fellow

    • Selected from 300+ applicants for a funded fellowship in AI agent security; red-teaming control protocols for LLM agents with evaluations built on ControlArena.
  • C

    Caisson AI

    Founder

    • Offline-first RAG assistant over equipment manuals for field technicians: ~92% retrieval accuracy, in paid pilots with elevator and heavy-equipment firms.
  • Q

    Quasi AI

    Software Engineering Intern

    • Productionized distributed simulation services; implemented PyTorch DDP multi-GPU training for a 2.3x speedup and 18% error reduction.
  • C

    Chicago Human+AI Lab

    Undergraduate Researcher

    • Prototyping multi-agent LLM pipelines that automate hypothesis generation, ranking, and evaluation over research literature.
  • C

    Calverton Growth

    Private Equity Intern

    • Deal sourcing and financial due diligence on manufacturing acquisitions.
  • M

    MIT Lincoln Laboratory

    Machine Learning Research Intern

    • First-authored the IEEE ICDM Best Paper on LLM watermark detection: 89% detection accuracy across 3 encoding schemes; cut the research pipeline's full-run compute from 48 to 6 hours.
  • N

    Northwestern University

    Research Intern

    • Built large-scale web scraping tools and applied ML clustering to analyze education data across Chicago Public Schools.

selected projects

view all

Caisson AI

Offline-first RAG over equipment manuals for field technicians: ~92% retrieval accuracy with fully on-device search, in paid pilots.

RAG
Next.js
FastAPI
Live Demo

Deferred-Execution Attacks

Defined a new attack class where LLM agents schedule harmful actions to fire after session monitoring ends, then built a trigger-graph monitor that closed the detection gap from 0/4 to 4/4. 1st place at Uncommon Hacks 2026.

LLM Agents
AI Security
ControlArena
DevpostWriteup

writing

view all

contact

The fastest way to reach me is email: wguo4@uchicago.edu. For anything longer, there's a form.