Related papers: Graph Diffusion Transformers for Multi-Conditional…
Diffusion models excel in image generation but lack detailed semantic control using text prompts. Additional techniques have been developed to address this limitation. However, conditioning diffusion models solely on text-based descriptions…
Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal…
De novo molecular generation from tandem mass spectra is a challenging inverse problem whose core difficulty lies in the circular dependency between atom-level and bond-level reasoning: determining a bond's type requires knowing its…
Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models…
We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy…
Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equivariance through architectural constraints such as…
Understanding and predicting interface diffusion phenomena in materials is crucial for various industrial applications, including semiconductor manufacturing, battery technology, and catalysis. In this study, we propose a novel approach…
Channel gain maps (CGMs) enable propagation-aware services in edge-intelligent wireless communication networks, while diffusion-based CGM construction is memory intensive for on-device training or adaptation. This letter proposes…
Automatic drum transcription (ADT) is traditionally formulated as a discriminative task to predict drum events from audio spectrograms. In this work, we redefine ADT as a conditional generative task and introduce Noise-to-Notes (N2N), a…
Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of a pretrained Diffusion Transformer (DiT) and find that physically plausible and implausible videos are…
We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the…
Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-Euclidean structured data. Such methods have shown promising results on a broad spectrum of applications…
Generative deep learning has become pivotal in molecular design for drug discovery, materials science, and chemical engineering. A widely used paradigm is to pretrain neural networks on string representations of molecules and fine-tune them…
Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…
Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). Their key idea is to disrupt images into noise through a fixed…
Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used to generate new, plausible data. However, current generative models are unable to work with…
Personalized image generation aims to produce images of user-specified concepts while enabling flexible editing. Recent training-free approaches, while exhibit higher computational efficiency than training-based methods, struggle with…
Inverse problems generally require a regularizer or prior for a good solution. A recent trend is to train a convolutional net to denoise images, and use this net as a prior when solving the inverse problem. Several proposals depend on a…
The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Since inverse problems inherently entail maximum a posteriori estimation,…