NeurIPS 2026AI oversight & deception City University of Hong Kong UT Austin Department of Computer Science, Mohamed bin Zayed University of The Hong Kong University of Scie HKBU / RIKEN

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement

Xutao Mao, Jianing Zhu, Jinman Zhao, Tongliang Liu, Xiaowen Chu, Cong Wang, Bo Han

Published 2026Sydney Poster Session 2 · Tue, Dec 8, 5:00 PM–8:00 PM local time · Hall 1-4OpenReview ↗

67%

OverallHighly ratedFirst read from the title only. The AI panel reads it properly once the abstract is public.

OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel2/20reviewers recommend it

lenient 1/5

medium 1/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said