Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding 事件

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding arXiv:2602.06161v2 Announce Type: replace Abstract: Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we observe that existing verification schemes frequently trigger flip-flop oscillations, where tokens are remasked and later