iiinova — where your digital self keeps evolving

Zilei Shao

@zoeshao.bsky.social

37 followers 30 following 4 posts

First-year Ph.D. Student @ StarAI Lab, UCLA Harvey Mudd College ‘24

Posts Replies Media

Reposted by Zilei Shao

Anji Liu @anjiliu.bsky.social · 02/05/2026

The answer is yes. To find out how, join our oral session or visit our poster: 🎤 𝐎𝐫𝐚𝐥 𝐏𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧: Tomorrow at 10:30 AM 🖼️ 𝐏𝐨𝐬𝐭𝐞𝐫 𝐒𝐞𝐬𝐬𝐢𝐨𝐧: Poster #177 (Tomorrow afternoon) Shout out to my amazing collaborators @zoeshao.bsky.social and @guyvdb.bsky.social for the incredible teamwork.

231

Zilei Shao @zoeshao.bsky.social · 04/03/2026

Check out our most recent in dLLM!

010

Zilei Shao @zoeshao.bsky.social · 11/03/2025

What happens if we tokenize cat as [ca, t] rather than [cat]? LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself. #AI #LLMs #tokenization #alignment

64815