Huo, Jiayan

1. T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation
   2025/05/01 by Guo, Xuyang, Huo, Jiayan, Shi, Zhenmei +3 · 13 citations
   #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help
   2025/03/10 by Cao, Yuefan, Guo, Xuyang, Huo, Jiayan +5 · 6 citations
   #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
3. RoPE Attention Can Be Trained in Almost Linear Time
   2024/12/23 by Yang Cao, Chen, Yifang, Jiayan Huo +8 · 3 citations
   Engineering · Computer Science · #Sparse and Compressive Sensing Techniques #Blind Source Separation Techniques #Neural Networks and Reservoir Computing
4. Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models
   2025/04/05 by Xuyang Guo, Guo, Xuyang, Zekai Huang +10 · 5 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
5. T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models
   2025/05/08 by Guo, Xuyang, Huo, Jiayan, Shi, Zhenmei +3 · 5 citations
   #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)