1 code implementation • 16 Mar 2024 • Sai Prasanna, Karim Farid, Raghu Rajan, André Biedenkapp
Toward the goal of ZSG to unseen variation in context, we propose the contextual recurrent state-space model (cRSSM), which introduces changes to the world model of the Dreamer (v3) (Hafner et al., 2023).
no code implementations • 10 Oct 2023 • Karim Farid, Simon Schrodi, Max Argus, Thomas Brox
LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation and focus on the important, semantic parts of the data.