Institution
University of TorontoRoles and affiliations follow the cited source. A source check is not an independent replication.
More filters → 
University of Waterloo
FAR.AIUniversity of Toronto
ETH Zurich
Massachusetts Institute of Technology
Vector Institute
QuestionHow robust are open-weight safeguards to modifications that preserve useful capability?
Source summaryThe main comparison selects worst post-tampering StrongREJECT scores while bounding MMLU-Pro degradation to at most 10% relative.
NUWA research note · independent review pending
QuestionDoes a narrow training objective generalize into unrelated misaligned responses rather than merely accepting harmful requests?
Source summaryEducational framing changes generalization despite matching insecure code.
NUWA research note · independent review pending · Contains: question / method / findings / interpretation / limits
QuestionHow should evaluation evidence constrain frontier development when tests cannot cover every risk?
Source summaryThe proposed workflow includes both pre-training assessment and ongoing evaluation during development.
NUWA research note · independent review pending
NUWA 
