4 papers
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
Ge Wu, Shen Zhang, Ruijing Shi +9
REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment betwee…
A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation
Yunheng Li, Zhongyu Li, Shanghua Gao +3
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences. However, we observe that existing methods are limit…
ChatAnything: Facetime Chat with LLM-Enhanced Personas
Yilin Zhao, Xinbin Yuan, Shanghua Gao +4
In this technical report, we target generating anthropomorphized personas for LLM-based characters in an online manner, including visual appearance, personality and tones, with onl…
Enhancing Representations through Heterogeneous Self-Supervised Learning
Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu +2
Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. How…