Qiang Qiu

9

Papers

27

Total Citations

Papers (9)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning

Sparse Fine-Tuning of Transformers for Generative Tasks

Consistency Posterior Sampling for Diverse Image Synthesis

Generative Quanta Color Imaging

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps

Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models

Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning