Lancaster University

MCMC and SMC samplers for the power distribution fail to converge under realistic compute budgets, and their reasoning gains are largely recreated by simple Best-of-N selection; Power-RLOO, which fine-tunes directly toward the power distribution, helps only when the base model is already aligned with the task.

MCMC and SMC samplers for the power distribution fail to converge under realistic compute budgets, and their reasoning gains are largely recreated by simple Best-of-N selection; Power-RLOO, which fine-tunes directly toward the power distribution, helps only when the base model is already aligned with the task.

Text-to-motion generation no longer needs a separate model per skeleton: once root-centered joint trajectories are arranged into joint-time images, image diffusion architectures share one motion autoencoder and one generator across HumanML3D and KIT-ML while keeping each dataset's native skeletal definition.

Text-to-motion generation no longer needs a separate model per skeleton: once root-centered joint trajectories are arranged into joint-time images, image diffusion architectures share one motion autoencoder and one generator across HumanML3D and KIT-ML while keeping each dataset's native skeletal definition.

Spatial prediction targets the conditional distribution of a latent spatial field given observations, which is rarely available in closed form and is hard to sample. Guided diffusion separates the two: an unconditional diffusion model is trained on the process model alone, and a differentiable likelihood gradient is added during reverse diffusion at prediction time, so one trained process model serves many data models. Across Gaussian processes, a Ginzburg–Landau amplitude field and a methane-flux inversion over the UK and Ireland, the predictive distributions match exact or MCMC results and scale linearly with the latent dimension at higher resolutions.

Spatial prediction targets the conditional distribution of a latent spatial field given observations, which is rarely available in closed form and is hard to sample. Guided diffusion separates the two: an unconditional diffusion model is trained on the process model alone, and a differentiable likelihood gradient is added during reverse diffusion at prediction time, so one trained process model serves many data models. Across Gaussian processes, a Ginzburg–Landau amplitude field and a methane-flux inversion over the UK and Ireland, the predictive distributions match exact or MCMC results and scale linearly with the latent dimension at higher resolutions.

The work represents polycrystalline microstructures as anisotropic power diagrams (APDs), learns a flow-matching generative model over their compact geometric parameters with a graph neural network, and introduces a C4-equivariant architecture so that rotations of the input noise produce corresponding rotations of the generated microstructure; a training-free guidance framework then generates morphologies qualitatively inspired by copper welds, cast metal slabs, 3D-printed stainless steel, and heterogeneous lamella titanium without retraining.

The work represents polycrystalline microstructures as anisotropic power diagrams (APDs), learns a flow-matching generative model over their compact geometric parameters with a graph neural network, and introduces a C4-equivariant architecture so that rotations of the input noise produce corresponding rotations of the generated microstructure; a training-free guidance framework then generates morphologies qualitatively inspired by copper welds, cast metal slabs, 3D-printed stainless steel, and heterogeneous lamella titanium without retraining.