Lichun Li
4 papers · 2024–2025 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
model compression
(3)
rank compression
(2)
large language model
(2)
privacy protection
(2)
adversarial attack
(1)
parameter-efficient fine-tuning
(1)
memory optimization
(1)
vertical federated learning
(1)
privacy leakage
(1)
gradient preservation
(1)
privacy-preserving fine-tuning
(1)
adversarial attack mitigation
(1)
rounding layer
(1)
layer-wise importance
(1)
importance-aware sparse tuning
(1)
offsite tuning
(1)
reinforcement learning
(1)
knowledge distillation
(1)
privacy preservation
(1)
Papers
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
ACL 2025
ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
AAAI 2025
Integer Is Enough: When Vertical Federated Learning Meets Rounding
AAAI 2024
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
EMNLP 2024