Abstract Low-Rank Adaptation (LoRA), which updates the dense neural network layers with
pluggable low-rank matrices, is one of the best performed parameter efficient fine-tuning …

Camouflaged object detection (COD) is the challenging task of identifying camouflaged
objects visually blended into surroundings. Albeit achieving remarkable success, existing …

Oriented object detection, an emerging task in recent years, aims to identify and locate
objects across varied orientations. This requires the detector to accurately capture the …

This paper identifies significant redundancy in the query-key interactions within self-attention
mechanisms of diffusion transformer models, particularly during the early stages of …

Recent studies have demonstrated the effectiveness of token-based methods for visual
content generation. As a representative work, non-autoregressive Transformers (NATs) are …

Diffusion Models are popular generative modeling methods in various vision tasks, attracting
significant attention. They can be considered a unique instance of self-supervised learning …

Test-time adaptation (TTA) aims to enhance the performance of source-domain pretrained
models when tested on unknown shifted target domains. Traditional TTA methods primarily …

As one of the most popular and sought-after generative models in the recent years, diffusion
models have sparked the interests of many researchers and steadily shown excellent …

Rectified-flow-based diffusion transformers, such as FLUX and OpenSora, have
demonstrated exceptional performance in the field of image and video generation. Despite …

Video editing is an emerging task, in which most current methods adopt the pre-trained text-
to-image (T2I) diffusion model to edit the source video in a zero-shot manner. Despite …