3 papers
cs.CV2025
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
Kun Liu, Qi Liu, Xinchen Liu +5
Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely gener…
cs.CV2025
Scaling Down Text Encoders of Text-to-Image Diffusion Models
Lifu Wang, Daqing Liu, Xinchen Liu +1
Text encoders in diffusion models have rapidly evolved, transitioning from CLIP to T5-XXL. Although this evolution has significantly enhanced the models' ability to understand comp…
cs.AI2024
LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation
Yijun Liu, Wu Liu, Xiaoyan Gu +3
The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant p…