Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision--language models (VLMs) suffer from high inference latency due to sequential token decoding. Diffusion-based models offer a promising alternative through parallel generation, but they still require multiple denoising iterations. Compressing multi-step denoising to a single step could further reduce latency, but often degrades textual coherence due to the mean-field bias introduced by token-factorized denoisers. To address this challenge, we propose \textbf{ECHO}, an efficient diffusion-based VLM (dVLM) for chest X-ray report generation. ECHO enables stable one-step-per-block inference via a novel Direct Conditional Distillation (DCD) framework, which mitigates the mean-field limitation by constructing unfactorized supervision from on-policy diffusion trajectories to encode joint token dependencies. In addition, we introduce a Response-Asymmetric Diffusion (RAD) training strategy that further improves training efficiency while maintaining model effectiveness. Extensive experiments demonstrate that ECHO surpasses state-of-the-art autoregressive methods, improving RaTE and SemScore by \textbf{64.33\%} and \textbf{60.58\%} respectively, while achieving an \textbf{$8\times$} inference speedup without compromising clinical accuracy.

翻译：摘要：胸部X光报告生成（CXR-RG）有望大幅减轻放射科医生的工作负担。然而，传统自回归视觉-语言模型（VLM）由于采用顺序式词元解码，存在高推理延迟的问题。基于扩散的模型通过并行生成提供了有前景的替代方案，但仍需要多次去噪迭代。将多步去噪压缩为单步可进一步降低延迟，但词元因子化解噪器引入的平均场偏差常导致文本连贯性下降。为解决这一挑战，我们提出用于胸部X光报告生成的高效扩散型VLM（dVLM）——**ECHO**。ECHO通过新颖的直接条件蒸馏（DCD）框架实现稳定的每步单步推理，该框架利用基于策略的扩散轨迹构建非因子化监督，编码联合词元依赖关系，从而缓解平均场限制。此外，我们提出响应非对称扩散（RAD）训练策略，在保持模型有效性的同时进一步提升训练效率。大量实验表明，ECHO超越现有最优自回归方法，将RaTE和SemScore分别提升**64.33%**和**60.58%**，同时实现**8倍**推理加速且不牺牲临床准确性。