Zhao Xu

5

Papers

27

Total Citations

Papers (5)

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs

UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs

NeurIPS 2025arXiv

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance