Changling Li

@ChanglingXavier

AI safety, multi-agent systems, and governance. Incoming PhD working with @maksym_andr and Rediet Abebe. Currently at @ETH_en and @MPI_IS.

Zurich, Switzerland

Pinned
Changling Li
@ChanglingXavier
May 25
🔍 We release our work on decomposing and measuring evaluation awareness in frontier LLMs, together with EvalAwareBench, a factor-controlled benchmark for measuring which environmental cues trigger recognition and whether models behave consistently once they recognize evaluation.
GIF
7
Changling Li
@ChanglingXavier
11h
Reviewer: “I still have questions about who would use this.” Me: 👉🏻
3
Changling Li
@ChanglingXavier
Sep 24
The new #ICLR email is basically telling me that I am qualified but not invited LOL 😭 Need to get invited to another party to pick up my self esteem 💔
2
Changling Li
@ChanglingXavier
Sep 23
Wow!
jonas wiedermann-möller
@j0wimo
Sep 16
Reuters wrote an article about my findings about two accounts on HF that got hijacked over by agents in May. The agents probed the HF infrastructure, in my opinion, could be early signals for what happened in July! Knowing this, it poses the question whether the Huggingface-OAI
Changling Li
@ChanglingXavier
Sep 22
There is nothing better than knowing your work is useful in production!
Maksym Andriushchenko
@maksym_andr
Sep 22
great to see @ChanglingXavier's master's thesis (arxiv.org/abs/2605.23055) cited in the Opus 5.5 system card! "We made this revision drawing on internal experiences and using the recommendations in Li et al., 2026."
1