相关论文: Guiding Diffusion Models with Semantically Degrade…

The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that…

Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process…

Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients…

Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately capture the subtle, category-defining features critical for…

Text-driven diffusion models have exhibited impressive generative capabilities, enabling various image editing tasks. In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of…

We study masked discrete diffusion models with classifier-free guidance (CFG). Assuming no score error nor discretization error, we derive an explicit solution to the guided reverse dynamics, so that how guidance influences the sampling…

Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been…

Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and…

We present Catalog Phrase Grounding (CPG), a model that can associate product textual data (title, brands) into corresponding regions of product images (isolated product region, brand logo region) for e-commerce vision-language…

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

Flow matching has demonstrated strong generative capabilities and has become a core component in modern Text-to-Speech (TTS) systems. To ensure high-quality speech synthesis, Classifier-Free Guidance (CFG) is widely used during the…

Diffusion models, while trained for image generation, have emerged as powerful foundational feature extractors for downstream tasks. We find that off-the-shelf diffusion models, trained exclusively to generate natural RGB images, can…

Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across domains to enhance recommendation quality. However, naive aggregation of sequential signals can introduce conflicting domain-specific preferences, leading to…

Open-vocabulary segmentation models such as SAM3 perform well across broad categories via text prompting, yet degrade when target classes are visually underrepresented in pretraining or depart from canonical depictions-limitations text…

Classifier-Free Guidance (CFG) has established the foundation for guidance mechanisms in diffusion models, showing that well-designed guidance proxies significantly improve conditional generation and sample quality. Autoguidance (AG) has…

ControlNet has enabled detailed spatial control in text-to-image diffusion models by incorporating additional visual conditions such as depth or edge maps. However, its effectiveness heavily depends on the availability of visual conditions…

We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density…

Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks…

Recent advances in large-scale text-to-image diffusion models have heightened concerns about their potential misuse, especially in generating harmful or misleading content. This underscores the urgent need for effective machine unlearning,…

Controllability is a fundamental requirement in video synthesis, where accurate alignment with conditioning signals is essential. Existing classifier-free guidance methods typically achieve conditioning indirectly by modeling the joint…