General world models represent a crucial pathway toward achieving Artificial General
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …

Recent advancements in large-scale visual-language pre-trained models have led to
significant progress in zero-/few-shot anomaly detection within natural image domains …

Brain decoding a pivotal field in neuroscience aims to reconstruct stimuli from acquired brain
signals primarily utilizing functional magnetic resonance imaging (fMRI). Currently brain …

Adversarial attacks constitute a notable threat to machine learning systems, given their
potential to induce erroneous predictions and classifications. However, within real-world …

The identification of sensory cues associated with potential opportunities and dangers is
frequently complicated by unrelated events that separate useful cues by long delays. As a …

This study explores the role of cross-attention during inference in text-conditional diffusion
models. We find that cross-attention outputs converge to a fixed point after few inference …

In the era of AIGC, the demand for low-budget or even on-device applications of diffusion
models emerged. In terms of compressing the Stable Diffusion models (SDMs), several …

Existing deep-learning-based methods for nighttime video deraining rely on synthetic data
due to the absence of real-world paired data. However, the intricacies of the real world …

We introduce a novel task named 'target speech diarization', which seeks to determine
'when target event occurred'within an audio signal. We devise a neural architecture called …

Vision transformers have achieved remarkable success in computer vision tasks by using
multi-head self-attention modules to capture long-range dependencies within images …