4 papers · 1 filter
Variational Learning for Insertion-based Generation
Yangtian Zhang, Zhe Wang, Arthur Gretton +4
Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generat…
Learn to Guide Your Diffusion Model
Alexandre Galashov, Ashwini Pokle, Arnaud Doucet +3
Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining condi…
Distributional Diffusion Models with Scoring Rules
Valentin De Bortoli, Alexandre Galashov, J. Swaroop Guntupalli +4
Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted.…
Accelerated Diffusion Models via Speculative Sampling
Valentin De Bortoli, Alexandre Galashov, Arthur Gretton +1
Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting t…