Related papers: MINDiff: Mask-Integrated Negative Attention for Co…

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences across multiple clients,…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Text-to-image diffusion models can generate stunning visuals, yet they often fail at tasks children find trivial--like placing a dog to the right of a teddy bear rather than to the left. When combinations get more unusual--a giraffe above…

Generating multiple new concepts remains a challenging problem in the text-to-image task. Current methods often overfit when trained on a small number of samples and struggle with attribute leakage, particularly for class-similar subjects…

Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…

The diffusion model is widely leveraged for either video generation or video editing. As each field has its task-specific problems, it is difficult to merely develop a single diffusion for completing both tasks simultaneously. Video…

We propose ADIOS, a masked image model (MIM) framework for self-supervised learning, which simultaneously learns a masking function and an image encoder using an adversarial objective. The image encoder is trained to minimise the distance…

Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens from a fully masked sequence. Their standard confidence-based unmasking strategy systematically defers high-entropy logical connective tokens, degrading…

Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive…

With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, trajectory similarity computation plays a critical role in a…

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on…

Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing…

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…

Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method…

Due to lack of fully publicly available text-to-video models, current video editing methods tend to build on pre-trained text-to-image generation models, however, they still face grand challenges in dealing with the local editing of video…

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider…

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Diffusion models, while increasingly adept at generating realistic images, are notably hindered by hallucinations -- unrealistic or incorrect features inconsistent with the trained data distribution. In this work, we propose Adaptive…

Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to…