PURL is introduced, a training-based framework that seamlessly unifies parallel generation with selective token revision and general principles of revisable decoding are revealed, suggesting that effective parallel generation depends not on revising more tokens, but on making the right commitments revisable at the righ...
Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-step generation remains a fundamental challenge. In this work, we introduce the Discrete Average Generator, a principled extension of MeanFlow to Continuous-Time Markov C...
Yi-Dong Ouyang, Zheng-Yan Wan, Themistoklis Haris et al.· arXiv.org· 0 citations
Sampling from unnormalized distributions over large discrete state spaces becomes difficult when a multimodal target is far from a tractable reference. We introduce Iterative Exact Discrete Guidance (IEDG), a population-exact, trajectory-wise guidance framework for unnormalized discrete targets. Rather than learn the f...
Yuwen Qian, Yi-Dong Ouyang, Zheng-Yan Wan et al.· 0 citations
Low-Entropy Discrete Flow (LEDFlow), a training-free sampler that adaptively orders absorption by local entropy, is proposed, and it is shown that, under entropy-error regularity, selecting the lowest-entropy positions under a fixed absorption count minimizes an upper bound on the conditional term.
Tung Sum Thomas Kwok, Yi-Dong Ouyang, Yingjia Wan et al.· 0 citations
This work introduces a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order and demonstrates that learning this control block substantially improves both text-to-image alignment and multimodal understanding in DLMs.
Yi-Dong Ouyang, Zhe Wang, Sourav S. Bhabesh et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.