AParadigmShift2026A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in VideosAllen He, Qi Liu, Kun Liu, Xinchen Liu, Wu LiuarXiv preprint
TIDE2026TIDE: Task-Isolated Diffusion for Unified Video Editing and GenerationQi Liu, Gang Yue, Mingyu Yin, Lisai Zhang, Yidi Wu, Yaole Wang, Yaohui Wang, Chang Yao, Jingyuan Chen, Lin MaarXiv preprint
HOIGen-1M2025HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video GenerationKun Liu, Qi Liu, Xinchen Liu, Jie Li, Yongdong Zhang, Jiebo Luo, Xiaodong He, Wu LiuarXiv preprint
TEMPLE2025TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT AlignmentShicheng Li, Lei Li, Kun Ouyang, Shuhuai Ren, Yuanxin Liu, Yuanxing Zhang, Fuzheng Zhang, Lingpeng Kong, Qi Liu, Xu SunarXiv preprint