Xiu Su

Consistency-Driven Calibration and Matching for Few-Shot Class Incremental Learning

Towards Robust Graph Unlearning via Gradient Consistency Control

DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training

CoopGuard : Cooperative Agents Safeguarding LLMs Against Evolving Adversarial Attacks

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

Stable Fair Graph Representation Learning with Lipschitz Constraint

On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging

MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization

Training-free Long Video Generation with Chain of Diffusion Model Experts

A Provable Quantile Regression Adapter via Transfer Learning