Related papers: Breaking the Factorization Barrier in Diffusion La…

Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited…

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…

With the proliferation of distributed data sources, Federated Learning (FL) has emerged as a key approach to enable collaborative intelligence through decentralized model training while preserving data privacy. However, conventional FL…

Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions given as endpoints. Despite their promising performance in tasks like image translation, DDBMs…

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed compared to purely discrete formulations. This gap is counterintuitive, given…

Generating photos satisfying multiple constraints find broad utility in the content creation industry. A key hurdle to accomplishing this task is the need for paired data consisting of all modalities (i.e., constraints) and their…

Modeling long-range dependencies in time series generation poses a fundamental trade-off between representational capacity and computational efficiency. Traditional temporal diffusion models suffer from local entanglement and the…

Masked diffusion models (MDMs) offer a compelling alternative to autoregressive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means potentially…

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory,…

We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial…

Training data has been proven to be one of the most critical components in training generative AI. However, obtaining high-quality data remains challenging, with data privacy issues presenting a significant hurdle. To address the need for…

Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories.…

Animating virtual avatars to make co-speech gestures facilitates various applications in human-machine interaction. The existing methods mainly rely on generative adversarial networks (GANs), which typically suffer from notorious mode…

Multimodal sentiment analysis remains a challenging task due to the inherent heterogeneity across modalities. Such heterogeneity often manifests as asynchronous signals, imbalanced information between modalities, and interference from…

We introduce a novel method to automatically generate an artistic typography by stylizing one or more letter fonts to visually convey the semantics of an input word, while ensuring that the output remains readable. To address an assortment…

Large Language Models (LLMs) often excel in specific domains but fall short in others due to the limitations of their training. Thus, enabling LLMs to solve problems collaboratively by integrating their complementary knowledge promises to…

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…

Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address…

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network…