This paper introduces IDLM, a method that accelerates discrete Diffusion Language Models by adapting inverse distillation techniques, achieving 4x-64x faster inference while maintaining generative quality through theoretically-validated unique solutions and stable gradient relaxations.

This paper introduces Inverse Poisson Flow Matching (IPFM), a new distillation method that significantly accelerates electrostatic generative models like PFGM by learning a generator to match the teacher’s electrostatic field, enabling high-quality sample generation in few steps.

Interaction Field Matching (IFM) generalizes Electrostatic Field Matching (EFM) by employing general interaction fields, including a quark-inspired solution to modeling challenges of EFM.

RealUID is a universal distillation framework that accelerates all matching models by incorporating real data into the distillation process without the need for GANs.

We propose Electrostatic Field Matching (EFM), a novel method inspired by the physics of capacitors, which uses a neural network to learn electrostatic fields for generative modeling and distribution transfer.