arXiv AI
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 9
C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
arXiv:2606. 08962v1 Announce Type: new Abstract: World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations.
arXiv AI
Sep 1
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
CF‑VLA introduces a two‑stage coarse‑to‑fine approach for vision‑language‑action policies, replacing multi‑step sampling with a coarse initialization that constructs an action‑aware starting point and a single‑step refinement that corrects residual errors. The coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed‑time refinement. Experiments on CALVIN and LIBERO demonstrate that CF‑VLA achieves a strong efficiency‑performance trade‑off, reducing action sampling latency by 75.4 % and achieving an 83.0 % real‑robot success rate, outperforming existing NFE=2 methods and matching or surpassing NFE=10 baselines.
arXiv AI
21h ago
Vision-Language Models Are Joint Denoisers in Robotic Action Generation
arXiv:2611.01215v2 Announce Type: replace-cross Abstract: Diffusion-based vision-language-action (VLA) models cascade pretrained vision-language models (VLMs) with diffusion action experts, but typic...
arXiv AI
Jun 9
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
arXiv AI
Sep 30
Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
arXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction add...
arXiv Machine Learning
Jul 8
Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
arXiv:2607. 06370v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.