3 papers indexed here
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.
Efficient sampling from Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and algorithms. Multiple steps are usually required to draw unbiased samples, for example, iterations of an MCMC algorithm or integration steps in a diffusion-based amortised sampler. However,...
This work proposes Large Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators, and iteratively resample individual variables conditioned on others using an LLM's next-token conditionals to produce a stationary distribution.
The teacher, an auxiliary behavior model, is trained to sample high-loss regions of the student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
