---
title: "GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07912v1"
permalink: "https://feed.astralor.com/items/itm_76e64ab941b48aca82f82b64"
published: "2026-11-05T12:27:38.000Z"
score: 57
channel: "tech"
tags: ["RAG","GuidedWAM","Training-Free Energy Guidance","World Action Models","Autonomous Driving World","WAMs","Conditioning","World"]
---

# GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving

## 速览

World action models (WAMs) for autonomous driving couple the driving policy and the visual world model in a single generative network whose objectives are fixed post-training. Conditioning on a new driving objective req…

## 关键点

- World action models (WAMs) for autonomous driving couple the driving policy and the visual world model in a single generative network whose objectives are fixed post-training.
- Conditioning on a new driving objective requires retraining.
- We study energy guidance as a general mechanism and present GuidedWAM, a model-agnostic framework for injecting driving objectives into frozen WAMs at sampling time.

## 全文

World action models (WAMs) for autonomous driving couple the driving policy and the visual world model in a single generative network whose objectives are fixed post-training. Conditioning on a new driving objective requires retraining. We study energy guidance as a general mechanism and present GuidedWAM, a model-agnostic framework for injecting driving objectives into frozen WAMs at sampling time. Our framework constructs each objective as differentiable energies on the sampler's intermediate clean-action estimate, which needs only forward access to the frozen model, and is stabilized by sampling-time guidance scheduling, per-energy normalization, and velocity-bounded correction. On the NAVSIM v2 hard-split, guidance improves all three frozen, publicly released WAMs by 1.8 to 3.6 EPDMS, averaged over three sampler seeds, and adds less than 10% to the sampling time per step. These results position energy guidance as a practical post-training control channel for WAMs.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_76e64ab941b48aca82f82b64