DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting
技术动态
来源：arXiv cs.RO发布时间待核实
arXiv:2608.29749v1 Announce Type: new Abstract: Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasing latency in online robot control. To address this issue, we introduce DriftingVLA, a native one-step VLA that generates a complete action chunk with a single action-expert forward pass.