Xiaofeng Cao

FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

Long-tailed Test-Time Adaptation for Vision-Language Models

Towards Robust and Realistic Human Pose Estimation via WiFi Signals

Value Shaping: Bias Reduction in Bellman Error for Deep Reinforcement Learning

Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction

Long-tailed Recognition with Model Rebalancing

Preference-driven Knowledge Distillation for Few-shot Node Classification

EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation

Beautifying Diffusion Models: Learning Context-Aware Filters for Robust Dense Prediction on Test-Time Corrupted Images

Time-variant Duo-image Inpainting via Interactive Distribution Transition Estimation

CRVR: Continuous Representation-Driven Video Frame Modulation Against rPPG Heart Rate Measurement