VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

Inference-time scaling matters to a curious lifelong learner as a promising paradigm to improve generative models especially when outputs must satisfy structural constraints or optimize downstream rewards.

Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider Masked Diffusion Model (MDM) and introduce MDM-VGB, a discrete diffusion sampler that augments…