Related papers: Controllable and Compositional Generation with Lat…

Building on the success of diffusion models, significant advancements have been made in multimodal image generation tasks. Among these, human image generation has emerged as a promising technique, offering the potential to revolutionize the…

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, like Stable Diffusion, cannot handle fine-grained part-level…

Spatial profiling technologies in biology, such as imaging mass cytometry (IMC) and spatial transcriptomics (ST), generate high-dimensional, multi-channel data with strong spatial alignment and complex inter-channel relationships.…

Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take…

Coarse-grained (CG) models provide an effective route to reducing the complexity of molecular simulations (MD), but conventional approaches depend heavily on long all-atom MD trajectories to adequately sample configurational space. This…

Although deep learning has achieved impressive advances in transient stability assessment of power systems, the insufficient and imbalanced samples still trap the training effect of the data-driven methods. This paper proposes a…

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather…

In the era of generative AI, deep generative models (DGMs) with latent representations have gained tremendous popularity. Despite their impressive empirical performance, the statistical properties of these models remain underexplored. DGMs…

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

This work studies the learning problem of the energy-based prior model and the multi-layer generator model. The multi-layer generator model, which contains multiple layers of latent variables organized in a top-down hierarchical structure,…

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features…

In this work, we introduce an unconditional video generative model, InMoDeGAN, targeted to (a) generate high quality videos, as well as to (b) allow for interpretation of the latent space. For the latter, we place emphasis on interpreting…

Energy-based models (EBMs) are a simple yet powerful framework for generative modeling. They are based on a trainable energy function which defines an associated Gibbs measure, and they can be trained and sampled from via well-established…

Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

Controllable layout generation aims to create plausible visual arrangements of element bounding boxes within a graphic design according to certain optional constraints, such as the type or position of a specific component. While recent…

Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…

Generating new molecules with specified chemical and biological properties via generative models has emerged as a promising direction for drug discovery. However, existing methods require extensive training/fine-tuning with a large dataset,…

Human motions are compositional: complex behaviors can be described as combinations of simpler primitives. However, existing approaches primarily focus on forward modeling, e.g., learning holistic mappings from text to motion or composing a…