Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang. Findings of the Association for Computational Linguistics: ACL 2022. 2022.

Ruiqing Zhang, Zhongjun He, Hua Wu, Haifeng Wang. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Lijie Wang, Yaozong Shen, Shuyuan Peng, Shuai Zhang, Xinyan Xiao, Hao Liu, Hongxuan Tang, Ying Chen, Hua Wu, Haifeng Wang. Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL). 2022.

Recent advances in text-to-video (T2V) generation with diffusion models have garnered significant attention. How ever, they typically perform well in scenes with a single object and motion, struggling in compositional scenarios with multiple objects and distinct motions to accurately reflect the semantic content of text prompts. To address these challenges, we propose StarVid, a plug-and-play, training-free method that improves semantic alignment between multiple subjects, their motions, and text prompts in T2V models. StarVid first employs large language models (LLMs) to perform two-stage motion trajectory planning based on the input prompt, providing object-level spatial priors that guide the generation process. These priors are then used to impose a spatial-aware loss that refines cross-attention (CA) maps, encouraging attention to be focused on distinct regions corresponding to different subjects. Furthermore, a syntax guided contrastive constraint is introduced to explicitly enhance the association between verbs and their corresponding nouns in the CA maps, thereby improving motion-subject binding. Both qualitative and quantitative evaluations demonstrate that the proposed framework significantly outperforms baseline methods, delivering videos of higher quality with improved semantic consistency.

We have inactivated pRb, p107, and p130 in astrocytes by transgenic expression of T (a truncated SV40 T antigen) under the GFAP promoter. Founder mice died perinatally with extensive expansion of neural precursor and anaplastic astrocyte populations. In astrocytes, aberrant proliferation and extensive apoptosis were induced. Using a conditional allele of T, early lethality was circumvented, and adult mice developed high-grade astrocytoma, in which regions of decreased apoptosis expressed activated Akt. Indeed, astrocytoma development was accelerated in a , but not , background. These studies establish a highly penetrant preclinical model for astrocytoma based on events observed in the human disease and further provide insight into the role of PTEN mutation in astrocytoma progression.