We have 3 of 13 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
We show that continuous bitstream diffusion (CoBit), originally developed for language modeling, provides a unified framework for joint and conditional multimodal generation using the same training and sampling protocol. Across image-text, speech-text and protein sequence-structure modeling, models are trained separate...
Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high-dimensional data. For these operations to be statistically meaningful, paths between observations should preferentially traverse high-likelihood regions. Existing scalable pullback constructions typically use a unimod...
A general statistical framework for studying asymptotically optimal noise-level allocation in diffusion training and an idealized independent-learner regime, intended to model temporal specialization in neural networks are developed.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
