← 研踪 PaperTrailarXiv:2611.22356 · v1
SR-VLA: Stall-Reduced VLA Execution via Predicted-Input Lookahead and Selective KV Cache Repair
首次提交 2026-11-17 16:08
版本更新 2026-11-17 16:08
雷达观测 2026-11-18 19:42
摘要
Vision-language-action (VLA) policies incur control stalls when inference blocks the next action chunk. Asynchronous early inference can hide latency, but its results may be inconsistent with the arriving actual inputs. Unconditional reuse risks acting on mismatched inputs, whereas full recomputation discards useful precomputation. We propose SR-VLA, combining predicted-input lookahead with selective KV cache repair. During current chunk execution, a lightweight action-conditioned predictor generates next-boundary visual observations and proprioceptive state. These predictions, together with the task instruction, drive the frozen VLA to precompute a speculative KV cache and action chunk. After real inputs are available to VLA, predicted--real differences and task conditions determine whether to accept the action chunk or trigger selective KV repair. On LIBERO, SR-VLA achieves and query speedups over the respective synchronous and OpenVLA-OFT baselines, while maintaining competitive average task success rates. Under target-motion perturbation, success remains baseline-comparable, with -- query speedup.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 16:08 · 最新观测版本
SR-VLA: Stall-Reduced VLA Execution via Predicted-Input Lookahead and Selective KV Cache Repair
Vision-language-action (VLA) policies incur control stalls when inference blocks the next action chunk. Asynchronous early inference can hide latency, but its results may be inconsistent with the arriving actual inputs. Unconditional reuse risks acting on mismatched inputs, whereas full recomputation discards useful precomputation. We propose SR-VLA, combining predicted-input lookahead with selective KV cache repair. During current chunk execution, a lightweight action-conditioned predictor generates next-boundary visual observations and proprioceptive state. These predictions, together with the task instruction, drive the frozen VLA to precompute a speculative KV cache and action chunk. After real inputs are available to VLA, predicted--real differences and task conditions determine whether to accept the action chunk or trigger selective KV repair. On LIBERO, SR-VLA achieves and query speedups over the respective synchronous and OpenVLA-OFT baselines, while maintaining competitive average task success rates. Under target-motion perturbation, success remains baseline-comparable, with -- query speedup.
查看此版本解读 →查看此版本原文 ↗