Papers
arxiv:2611.25667

CauSyncVLA: Causal Latent World Modeling for Asynchronous Robot Control

Published on Nov 19
Authors:
,
,
,
,
,
,
,
,

Abstract

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 5.04times inference throughput, improving closed-loop robustness and robot motion smoothness.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.25667
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.25667 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.25667 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.