3 papers indexed
Songchun Zhang, Sitong Guo, Xianghao Kong, Pengwei Liu, Yuwei Guo, Lvmin Zhang, et al.
Generative video compositing, which involves inserting external assets seamlessly into existing video sequences, is essential for content creation and visual effects. However, existing approaches suffer from a control-fidelity trade-off: they either hallucinate motion from static…
Yinhan Zhang, Dingwei Tan, Xianghao Kong, Yue Ma, Yeying Jin, Anyi Rao
Large-scale video diffusion models deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require…
Hohin Kwan, Hongyu Li, Ray Zhang, Manyuan Zhang, Xianghao Kong, Anyi Rao, et al.
Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events in individual frames? This ability, which we refer to as video temporal-logical reasoning, requires m…