← 研踪 PaperTrailarXiv:2611.25667 · v1
CauSyncVLA: Causal Latent World Modeling for Asynchronous Robot Control
首次提交 2026-11-19 15:45
版本更新 2026-11-19 15:45
雷达观测 2026-11-20 19:58
摘要
Vision-Language-Action (VLA) policies must react while visual inference is still running. Overlapping computation and execution reduces waiting, yet leaves perceptual memory stale and successive action chunks disconnected. We present CauSyncVLA, an asynchronous dual-system controller that aligns perceptual-memory prediction and trajectory correction with actual robot execution. Rather than forecasting pixels or physical states, a Causal Latent World Model predicts current perceptual memory from delayed visual anchors and executed state-action history, supervised through action-sensitive distillation to retain the frozen expert's control response. Conditioned on this updated memory, Predictive Flow Warm-Starting (PFWS) aligns the unexecuted action horizon for single-step flow correction without extra training. On LIBERO-10, CauSyncVLA reaches 93.8% success at 5.04 inference throughput, improving closed-loop robustness and robot motion smoothness.
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 · 2026-11-19 15:45 · 最新观测版本
CauSyncVLA: Causal Latent World Modeling for Asynchronous Robot Control
Vision-Language-Action (VLA) policies must react while visual inference is still running. Overlapping computation and execution reduces waiting, yet leaves perceptual memory stale and successive action chunks disconnected. We present CauSyncVLA, an asynchronous dual-system controller that aligns perceptual-memory prediction and trajectory correction with actual robot execution. Rather than forecasting pixels or physical states, a Causal Latent World Model predicts current perceptual memory from delayed visual anchors and executed state-action history, supervised through action-sensitive distillation to retain the frozen expert's control response. Conditioned on this updated memory, Predictive Flow Warm-Starting (PFWS) aligns the unexecuted action horizon for single-step flow correction without extra training. On LIBERO-10, CauSyncVLA reaches 93.8% success at 5.04 inference throughput, improving closed-loop robustness and robot motion smoothness.
查看此版本解读 →查看此版本原文 ↗