Jian Liang

15

Papers

100

Total Citations

Papers (15)

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Exploring Vacant Classes in Label-Skewed Federated Learning

Protecting Model Adaptation from Trojans in the Unlabeled Data

Backdoor Defense via Test-Time Detecting and Repairing