Search papers, labs, and topics across Lattice.
V鈥檚 implicit motion prior to enhance consistency and expressiveness, while a mixed subjective-objective reviewer enables reliable iterative refinement. We also collect a human-annotated CSG benchmark with ground-truth. Experiments show AnimeAgent achieves SOTA performance in consistency, prompt fidelity, and stylization. AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist? Hailong Yan1,2, Shice Liu2, Tao Wang2, Xiangtao Zhang1, Y. Zhang is affiliated with the School of Mathematical Sciences, Beijing University of Posts and Telecommunications, Beijing, China. J. Zhang is affiliated with the School of Mathematical Sciences, Beijing University of Posts and Telecommunications, and with the Key Laboratory of Mathematics and Information Networks (Beijing University of Posts and Telecommunications), Ministry of Education, Beijing, China. T. Wang is affiliated with the Institute of Statistics and Big Data, Renmin University of China, Beijing, China. Correspondence: J. Zhang .Email: jyzhang2024@bupt.edu.cn
1
0
3
0
Autoregressive inference gets a potential 14x speed boost without retraining, thanks to a clever trick of reusing attention weights within semantically coherent chunks.
