6 papers
CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization
Tewodros Ayalew, Matthew Jeung, Samuel Wheeler +5
We introduce CLAW, a fully end-to-end self-supervised framework for learning a world model jointly with continuous latent action representations directly from action-free videos. O…
Residual Connections Harm Generative Representation Learning
Xiao Zhang, Ruoxi Jiang, William Gao +2
We show that introducing a weighting factor to reduce the influence of identity shortcuts in residual networks significantly enhances semantic feature learning in generative repres…
HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields
Sudarshan Babu, Phillip Lo, Xiao Zhang +5
We introduce HyperDiffusionFields (HyDiF), a framework that models 3D molecular conformers as continuous fields rather than discrete atomic coordinates or graphs. At the core of ou…
Hierarchical Implicit Neural Emulators
Ruoxi Jiang, Xiao Zhang, Karan Jakhar +4
Neural PDE solvers offer a powerful tool for modeling complex dynamical systems, but often struggle with error accumulation over long time horizons and maintaining stability and ph…
Latent Intrinsics Emerge from Training to Relight
Xiao Zhang, William Gao, Seemandhar Jain +3
Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphics schemes recover an explicit representation of…
Nested Diffusion Models Using Hierarchical Latent Priors
Xiao Zhang, Ruoxi Jiang, Rebecca Willett +1
We introduce nested diffusion models, an efficient and powerful hierarchical generative framework that substantially enhances the generation quality of diffusion models, particular…