相关论文: GLA-Grad++: An Improved Griffin-Lim Guided Diffusi…

Data augmentation is gaining importance across various aspects of time series analysis, from forecasting to classification and anomaly detection tasks. We introduce the Latent Generative Transformer Augmentation (L-GTA) model, a generative…

Language-queried Audio Source Separation (LASS) enables open-vocabulary sound separation via natural language queries. While existing methods rely on task-specific training, we explore whether pretrained diffusion models, originally…

Most existing Vision-Language-Action (VLA) models rely primarily on RGB information, while ignoring geometric cues crucial for spatial reasoning and manipulation. In this work, we introduce GLaD, a geometry-aware VLA framework that…

To stabilize the training of Large Language Models (LLMs), gradient clipping is a nearly ubiquitous heuristic used to alleviate exploding gradients. However, traditional global norm clipping erroneously presupposes gradient homogeneity…

Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling. However, prevailing VL approaches are limited by the requirement for labeled data and the use of complex multi-step pretraining objectives. We present MAGMA…

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

In this paper, we present a Diffusion GAN based approach (Prosodic Diff-TTS) to generate the corresponding high-fidelity speech based on the style description and content text as an input to generate speech samples within only 4 denoising…

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm,…

Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to generate image data? For…

Real-world speech is often corrupted by multiple degradations simultaneously, including additive noise, reverberation, and nonlinear distortion. Diffusion-based enhancement methods perform well on single degradations but struggle with…

The growing population of L2 English speakers has increased the demand for developing automatic graders for spoken language assessment (SLA). Historically, statistical models, text encoders, and self-supervised speech models have been…

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…

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…

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Recently, diffusion models have excelled in image generation tasks and have also been applied to neural language processing (NLP) for controllable text generation. However, the application of diffusion models in a cross-lingual setting is…

Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be degraded. Recent studies show that incorporating a GAN…

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…