Related papers: Gated Condition Injection without Multimodal Atten…

Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein--ligand compatibility and multi-objective drug-like properties, yet existing methods often optimize these constraints in isolation, failing to…

Recent advancements in 3D diffusion-based semantic scene generation have gained attention. However, existing methods rely on unconditional generation and require multiple resampling steps when editing scenes, which significantly limits…

Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are…

Diffusion models have recently shown strong progress in generative tasks, offering a more stable alternative to GAN-based approaches for makeup transfer. Existing methods often suffer from limited datasets, poor disentanglement between…

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention…

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse weather scenarios encompass multiple possibilities, and…

In recent years, significant progress has been made in the development of text-to-image generation models. However, these models still face limitations when it comes to achieving full controllability during the generation process. Often,…

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block…

Single-cell RNA sequencing (scRNA-seq) data are important for studying the laws of life at single-cell level. However, it is still challenging to obtain enough high-quality scRNA-seq data. To mitigate the limited availability of data,…

Automated creation of synthetic traffic scenarios is a key part of validating the safety of autonomous vehicles (AVs). In this paper, we propose Scenario Diffusion, a novel diffusion-based architecture for generating traffic scenarios that…

Deep generative models, such as generative adversarial networks and diffusion models, have recently emerged as powerful tools for planning tasks and behavior synthesis in autonomous systems. Various guidance strategies have been introduced…

We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process. As data is progressively corrupted by noise, only a small number of features remain informative for…

Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative…

Controllable layout generation aims at synthesizing plausible arrangement of element bounding boxes with optional constraints, such as type or position of a specific element. In this work, we try to solve a broad range of layout generation…

Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per…

Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier…

As 3D point clouds become the prevailing shape representation in computer vision, generating high-quality point clouds remains a challenging problem. Flow-based models have shown strong potential due to exact likelihood estimation and…

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…