Jian Liang

39

Papers

100

Total Citations

Papers (39)

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

Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free Approach

Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation

Additive Adversarial Learning for Unbiased Authentication

Domain Adaptation With Auxiliary Target Domain-Oriented Classifier

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

Causality Inspired Representation Learning for Domain Generalization

Improving Generalization With Domain Convex Game

Mind the Label Shift of Augmentation-Based Graph OOD Generalization

Semantic Concentration for Domain Adaptation

TALL: Thumbnail Layout for Deepfake Video Detection

Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation

A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

DINE: Domain Adaptation From Single and Multiple Black-Box Predictors

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

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

Pareto Domain Adaptation

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

Contrastive Graph Structure Learning via Information Bottleneck for Recommendation

Synergy-of-Experts: Collaborate to Improve Adversarial Robustness

Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation