Xin Yi
3 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (1)
ACL (1)
CVPR (1)
Top co-authors
Keywords
safety realignment
(2)
autonomous driving
(1)
network pruning
(1)
model safety
(1)
deep learning
(1)
parameter efficient
(1)
gaze prediction
(1)
model pruning
(1)
adversarial attack
(1)
perturbation robustness
(1)
vision-language model
(1)
attention head
(1)
fine-tuning attack
(1)
parameter efficient tuning
(1)
visual naturalness
(1)
neuron transplantation
(1)
alignment safety
(1)
physical world adversarial attack
(1)
object detection
(1)
neuron restoration
(1)
Papers
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
AAAI 2025
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
ACL 2025
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
CVPR 2023