Zesheng Shi
3 papers · 2025–2026 · 1 venue · 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 ↓
🗺️
Taxonomy Completionist
(11)
Venues
Top co-authors
Research topics
Keywords
jailbreak attack
(2)
model editing
(1)
harmful content
(1)
safety alignment
(1)
model alignment
(1)
backdoor attack
(1)
synthetic data
(1)
self-play fine-tuning
(1)
knowledge localization
(1)
neuron pruning
(1)
adaptive weighting
(1)
harmful response
(1)
large language model
(1)
reinforcement learning with verifiable reward
(1)
asymmetric chain backdoor
(1)
knowledge unlearning
(1)
poisoning data
(1)