用扩散模型生成动作候选，再用视觉语言模型单次评分选最优，提升机器人任务成功率。
Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model
- 扩散模型生成多个动作候选，视觉语言模型单次评分选优
- 仿真环境下成功率提升4.3点，真实世界提升19.7点
- 适合需要高精度与强泛化的机器人控制任务
视觉-语言-动作（VLA）模型在具身任务中表现优异。当前VLA多采用扩散动作专家高效生成高精度连续动作块，而自回归生成在低层控制上较慢且准确率较低。然而自回归范式仍能提供互补先验，提升分布外场景下的鲁棒性与泛化能力。为此，我们提出动作草稿与验证框架（ADV）：扩散动作专家生成多个候选动作块，视觉语言模型通过类似困惑度的指标在单次前向传播中对所有候选进行评分并选择最优。在相同骨干网络、训练数据和动作块长度条件下，ADV在仿真环境中成功率提升4.3个百分点，在真实世界中提升19.7个百分点，仅增加一次VLM重排序开销。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while auto-regressive generation can be slower and less accurate at low-level control. Yet auto-regressive paradigms still provide complementary priors that can improve robustness and generalization in out-of-distribution environments. To leverage both paradigms, we propose Action-Draft-and-Verify (ADV): diffusion action expert drafts multiple candidate action chunks, and the VLM selects one by scoring all candidates in a single forward pass with a perplexity-style metric. Under matched backbones, training data, and action-chunk length, ADV improves success rate by +4.3 points in simulation and +19.7 points in real-world over diffusion-based baseline, with a single-pass VLM reranking overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。