Weikai Lu
3 papers · 2025–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
Top co-authors
Research topics
Keywords
safety alignment
(2)
multimodal large language model
(2)
model safety
(1)
responsible ai
(1)
adversarial defense
(1)
fine-tuning attack
(1)
low-resource setting
(1)
security vulnerability
(1)
activation steering
(1)
large language model alignment
(1)
model capability
(1)
synthetic embedding
(1)
malicious fine-tuning
(1)
indirect prompt injection
(1)
large language model
(1)
model defense
(1)
low-resource training
(1)
capability degradation
(1)
harmful instruction
(1)
safety-utility trade-off
(1)