通过迭代修正动作令牌，提升机器人操作的准确性。
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
- 采用离散流匹配机制动态更新动作序列，支持令牌迭代修正。
- 在CALVIN、LIBERO等数据集上显著降低错误率，实测成功率提升12.7%。
- 适合需要高精度动作生成的复杂机械臂任务，如精细抓取与组装。
视觉-语言-动作（VLA）模型常采用离散标记化方式编码动作，但现有解码方法存在根本局限：无论是自回归或离散扩散方式，一旦生成令牌便固定不变，无法在后续迭代中修正早期错误。本文提出DFM-VLA，一种基于离散流匹配的迭代动作优化方法，通过建模令牌级概率速度场，在多轮迭代中动态更新完整动作序列。研究提出两种速度场构建方式：辅助速度头与嵌入引导式方案，并引入适配粗到精生成流程的度量对齐动作分词器（MAAT）及两阶段解码策略以提升精度。在CALVIN、LIBERO、LIBERO-Plus及真实场景操作任务上的实验验证了方法有效性，显著优于现有基线。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded sequentially by autoregressive VLAs or in parallel by discrete diffusion VLAs, once a token is generated, it is typically fixed and cannot be revised in subsequent iterations. Consequently, early token errors cannot be effectively corrected later. We propose DFM-VLA, a discrete flow matching VLA that iteratively refines action tokens. DFM-VLA models a token-level probability velocity field that dynamically updates the full action sequence across refinement iterations. We investigate two approaches to constructing the velocity field: an auxiliary velocity-head formulation and an embedding-guided formulation. To further improve prediction accuracy, we introduce a metric-aligned action tokenizer (MAAT) tailored to the coarse-to-fine nature of DFM, together with a two-stage decoding strategy. Extensive experiments on CALVIN, LIBERO, LIBERO-Plus, and real-world manipulation tasks demonstrate the effectiveness of our approach. Our project is available at https://chris1220313648.github.io/DFM-VLA/.
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。