Wenshuo Chen

CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model

SM: Bridging the Robustness Gap in Clinical Time Series Analysis via Hierarchical Stability Optimization

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models

Attention Smoothing: Correcting Causal Bias in Autoregressive Language Models

From Model Fusion to Layer Fusion: A Weight Perspective

DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space

Evaluating the Unseen: A Novel Framework for Assessing Unsupervised Concept Bottleneck Models