LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection

ArXi:2605.10980v1 Announce Type: cross Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence levels, which ensures negligible discrepancy between the marginal and joint distributions. However, the stringent confidence thresholds required to preserve accuracy severely constrain the scalability of parallelism.