论文：将掩码扩散模型并行解码映射为随机序贯吸附过程
Masked diffusion as random sequential adsorption: an exactly solvable model for parallel decoding
把扩散模型的并行解码误差算出了物理精确解，还给出更优的 unmasking 策略，做生成模型的理论值得看看。
一篇 arXiv 论文（编号 2611.07845）把 masked diffusion 模型的并行解码误差与统计物理中的多粒子驱动系统联系起来。论文证明并行生成的误差等价于生成过程相对逆掩码过程的熵产生，并在 Markov 数据下将生成过程转化为随机序贯吸附（random sequential adsorption）问题，给出任意步数的精确解。解显示文本相关性越长，误差越集中在生成初期，因此开头采用小步长的 unmasking schedule 在路径误差和困惑度上都更优，且所需步数更少。最优 schedule 对应一个由 token 间互信息导出的热力学度量的测地线。
Masked diffusion as random sequential adsorption: an exactly solvable model for parallel decoding
Masked diffusion models generate text by reversing a stochastic masking process. Unlike autoregressive LLMs, which generate text one token at a time, they can reveal many tokens in parallel, at the price of an error, since tokens revealed together are drawn independently. We show that this trade-off maps onto the statistical physics of driven many-particle systems. (i) For any data, the error of parallel generation is the entropy production of the generation process relative to the reversed masking process. (ii) For Markov data, generation is a random sequential adsorption process with labelled gaps, which we solve exactly for any number of steps. (iii) For many steps, the error becomes the dissipation of a slowly driven system: the unmasking schedule plays the role of the driving protocol, the number of steps that of its duration, and the error is set by a thermodynamic metric that we obtain in closed form from the mutual information between tokens. Optimal schedules are geodesics of this metric. The exact solution shows how correlations in the text shape both the error and the quality of the output. The longer the correlations, the more the error concentrates at the start of generation. Schedules that start with small steps then gain more, both in path error and in perplexity, and need fewer steps to reach their asymptotic behaviour.