Tag
This paper introduces G-RRM, a neuro-symbolic approach that uses recurrent reasoning models to guide symbolic solvers for constraint satisfaction problems, showing significant speedups in certain conditions.
Introduces Spectral Guidance, a framework for controlling diffusion models by leveraging low-dimensional representations of the diffusion process, enabling flexible and stable control without task-specific retraining or backpropagation through the denoiser.
Flow-Direct introduces a non-parametric guidance field for flow-based generative models that accumulates reward feedback persistently, improving feedback efficiency and enabling reuse of collected samples to guide generation for multiple objectives without additional reward evaluations.