Search Results for author:
Found 2 papers, 0 papers with code
Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors
We propose denoising diffusion variational inference (DDVI), an approximate inference algorithm for latent variable models which relies on diffusion models as flexible variational posteriors.
Active Preference Inference using Language Models and Probabilistic Reasoning
To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
