Technology
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
In this paper, we propose QT -ViT models that improve the previous linear self-attention using quadratic Taylor expansion.
Equivariant flow matching
Our main contributions in this work are as follows: 1.
GACL: Exemplar-Free Generalized Analytic Continual Learning
Class incremental learning (CIL) trains a network on sequential tasks with separated categories in each task but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks.
Pairwise GUI Dataset Construction Between Android Phones and Tablets
GUIs development to enhance developers' productivity.
Gradient-free Decoder Inversion in Latent Diffusion Models
For example, recent video LDMs can generate more than 16 frames, but GPUs with 24 GB memory can only perform gradient-based decoder inversion for 4 frames.
Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
DA operations, we reveal that both ample spatial diversity and slight hardness are indispensable.