Search Results for author:
Found 3 papers, 0 papers with code
Compress Guidance in Conditional Diffusion Sampling
Enforcing guidance throughout the entire sampling process often proves counterproductive due to the model-fitting issue., where samples are generated to match the classifier's parameters rather than generalizing the expected condition.
Boosting Diffusion Models with an Adaptive Momentum Sampler
Our proposed sampler can be readily applied to a pre-trained diffusion model, utilizing momentum mechanisms and adaptive updating to smooth the reverse sampling process and ensure stable generation, resulting in outputs of enhanced quality.
Optimization of a Real-Time Wavelet-Based Algorithm for Improving Speech Intelligibility
Various gains are applied to the sub-band signals before they are recombined to form a modified version of the speech.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
