Related papers: No Safe Dose: How Training Data Drives Unsafe Imag…

Text-to-image diffusion models achieve high-fidelity image generation from natural language prompts. ControlNets extend these models by enabling conditioning on structural inputs (e.g., edge maps, depth, pose), providing fine-grained…

Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising…

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…

The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of…

Image segmentation is a crucial vision task that groups pixels within an image into semantically meaningful segments, which is pivotal in obtaining a fine-grained understanding of real-world scenes. However, an increasing privacy concern…

The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…

Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…

Text-to-image models are trained using large datasets of image-text pairs collected from the internet. These datasets often include copyrighted and private images. Training models on such datasets enables them to generate images that might…

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the…

Size of the training dataset is an important factor in the performance of a machine learning algorithms and tools used in medical image processing are not exceptions. Machine learning tools normally require a decent amount of training data…

Text-to-image diffusion models excel at generating images from natural language descriptions, yet fail to interpret numerical colors such as hex codes (#FF5733) and RGB values (rgb(255,87,51)). This limitation stems from subword…

Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with…

AI-based code generators have gained a fundamental role in assisting developers in writing software starting from natural language (NL). However, since these large language models are trained on massive volumes of data collected from…

Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

The increasing prevalence of synthetic data in training loops has raised concerns about model collapse, where generative models degrade when trained on their own outputs. While prior work focuses on this self-consuming process, we study an…

While video compression algorithms effectively reduce bitrate, aggressive quantization often compromises temporal coherence, introducing artifacts such as flicker, motion inconsistency, and unstable textures. Although spatial quality…