# OSWAM preprint reports one-step action generation with approximately 3× speedup

_Published Monday, October 26, 2026 at 11:06 PM EDT · AI, Robotics, Science · Latest · Tier 2 — Notable_

Researchers report that OSWAM, a model that generates actions for autonomous driving and embodied control, achieves approximately 3× speedup over direct-policy World Action Model baselines. Their preprint reports compiled inference latency as low as 40ms on an NVIDIA RTX 5090 GPU.

OSWAM initializes action generation with learned representations that supply physical guidance, then generates actions in one diffusion step. The researchers also transfer information about future conditions during training. They report comparable or better experimental results than models requiring tens of steps; the findings concern experimental performance rather than deployed driving systems.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.35850v1)

---
Canonical: https://techandbusiness.org/newswire/vQQ1XszInNXdT8mHVeL-pb
Published: 2026-10-27T03:06:29.164Z
Story chronology: 2026-10-26T17:57:09.000Z
Retrieved: 2026-10-27T06:36:19.246Z
Publisher: Tech & Business (techandbusiness.org)