Asia
Single Image Reflection Separation via Dual-Stream Interactive Transformers
The main reasons come from the lack of concern on the feature correlation during interaction, and the limited receptive field. To remedy these deficiencies, this paper presents a Dual-Stream Interactive Transformer (DSIT) design.
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
TKGs, TKG representation learning poses great challenges to the research community.
FilterNet: Harnessing Frequency Filters for Time Series Forecasting Kun Yi
While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting.
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
We adopt a multi-armed bandit framework for this process, enhancing prompt selection based on the returns from online trajectories.
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i.e., sources of variation) and aims to
