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
Many-shot in-context learning (ICL) enables large language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration examples, but this paradigm shifts the inference efficiency bottleneck to the key-value (KV) cache memory. Due to the linear scaling behavior of the KV cache, storing these in...