Mushui Liu

6

Papers

65

Total Citations

Papers (6)

LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning

Improving Zero-Shot Generalization for CLIP with Variational Adapter

TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance

MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis