WAMJET: A Harness for World Action Model Acceleration

Le Chen; Lixin Liu; Jan Schneider; Zeju Qiu; Simon Guist; Bernhard Schölkopf; Dieter Büchler

cs.CVOct 1, 2026

WAMJET: A Harness for World Action Model Acceleration

Authors: Le Chen, Lixin Liu, Jan Schneider, Zeju Qiu, Simon Guist, Bernhard Schölkopf, Dieter Büchler

Organizations: Max Planck Institute for Intelligent Systems, Tubingen, Germany · The Chinese University of Hong Kong, Hong Kong SAR, China · Johannes Kepler University Linz, Austria

Abstract

World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although existing acceleration techniques offer many ways to reduce this cost, selecting and composing them requires substantial engineering for each model and hardware platform. To tackle this bottleneck, we present WAMJET, an agentic harness that accelerates WAM inference by equipping coding agents with reusable optimization guidance and measurement and validation tools. WAMJET follows a bottleneck-driven workflow where the agent profiles inference, modifies targeted code, validates effects, and iteratively refines the acceleration stack as bottlenecks shift, while preserving action quality. Experiments span six WAMs, three coding agents, and two GPU architectures. WAMJET achieves up to 9.95x lossless speedup over upstream implementations. Approximation and hardware-aware optimization yield additional latency reductions, with comparable success rates. The results show that WAMJET can produce effective acceleration stacks for WAM deployment.

Figures & tables

Fig. 1 : Overview of WAMJET. (A) Manual optimization requires diverse domain expertise, with substantial engineering for each deployment. (B) A coding agent without guidance may only apply generic optimizations while leaving deeper optimization opportunities unexplored. (C) WAMJET equips the agent with reusable guidance and tools for faster startup, bottleneck analysis, hardware-aware optimization, and iterative validation, supporting acceleration strategies tailored to different WAMs and GPU architectures.

Fig. 2 : WAMJET’s bottleneck-driven optimization workflow. The agent reduces startup costs, profiles inference to identify bottlenecks, explores lossless acceleration followed by approximate techniques when permitted, and validates candidates. The agent retains accepted changes, reassesses the remaining bottlenecks, and continues searching within the specified budget.

Component	Function
Agent guidance
Run configuration	Defines policy, checkpoint, workload, quality requirements, and search budget limits.
Optimization skill	Provides procedures for bottleneck analysis, code changes, accept/revert decisions, and validation.
External memory	Records validated notes for reuse across optimization runs.
Execution and Analysis
Policy runner	Runs the policy with reference checks, timing measurement, and run records.

TABLE I : Functional components of the WAMJET harness.

LLM	WAM	Baseline	w/o WAMJET		w/ WAMJET Lossless (Ours)
LLM	WAM	Latency (ms)	Latency (ms)	Speedup	$R_{1}$ Latency (ms) $\ast$	$R_{2}$ Latency (ms) $\ast$	$R_{1}$ / $R_{2}$ $\dagger$	Speedup $\ddagger$
GPT-5.6-sol	Fast-WAM	84.7	59.2	1.43x	50.4	37.4	1.35x	2.27x
	Cosmos-Policy	384.2	369.2	1.04x	236.2	163.1	1.45x	2.36x
	DreamZero	2780.7	2687.7	1.03x	2373.9	2030.6	1.17x	1.37x
	LingBot-VA	5323.6	2670.2	1.99x	755.8	686.5	1.10x	7.75x
Claude-opus-5	Fast-WAM	84.7	54.1	1.57x	47.5	43.1	1.10x	1.96x

TABLE II : Latency on H100 across baseline, w/o WAMJET, and w/ WAMJET Lossless across LLMs and WAMs.

WAM	GPU	Baseline	w/ WAMJET Lossless		w/ WAMJET Approx.
WAM	GPU	Latency (ms)	Latency (ms)	Speedup	Latency (ms)	Speedup	Approx. Method
DreamZero	H100	2780.7	1785.2	1.56x	1297.0	2.14x	FP8
DreamZero	B200	1598.5	823.9	1.94x	722.6	2.21x	NVFP4 + FP8
Cosmos3-Nano-Policy-DROID	H100	814.8	768.8	1.06x	651.2	1.25x	FP8
Cosmos3-Nano-Policy-DROID	B200	446.3	368.3	1.21x	304.7	1.47x	MXFP8

TABLE III : Latency of two WAMs under baseline and different WAMJET acceleration levels on two GPU architectures.

Fig. 3 : Optimization progress over search time for DreamZero (top) and OpenWAM (bottom) on B200.

WAM	Configuration	Approx. Method	Success Rate
DreamZero	Baseline	-	25.0%
	w/ WAMJET Lossless	-	24.0%
	w/ WAMJET Approx.	FP8	26.0%
	w/ WAMJET Approx.	NVFP4 + FP8	25.0%
Cosmos3-Nano-Policy	Baseline	-	43.0%
	w/ WAMJET Lossless	-	47.0%

TABLE IV : RoboLab subset success rates of Cosmos3-Nano-Policy-DROID and DreamZero under baseline and different WAMJET acceleration levels.

Config	Precision	Latency (ms)	Speedup	LIBERO	LIBERO-plus
Baseline	BF16	87.25	1.00x	98.95%	69.27%
w/ WAMJET Lossless	BF16	32.69	2.67x	99.10%	69.24%
w/ WAMJET Approx.	FP8	31.70	2.75x	99.25%	69.30%

TABLE V : Latency and success rates for OpenWAM.

Explore similar work

RealtimeWAM: How Fast Can I Run My World Action Model?
Oct 7, 2026Huanan Liu, Ye Li, Kangye Ji +8
Tsinghua University · YuanxingGuangnian Robotics · Nanjing University
Faster-WAM: Do World Action Models Need Deep Action Modules?
Aug 3, 2026Liheng Ma, Rui Heng Yang, Amin Abyaneh +8Faster-Wam Action Prediction
Huawei Noah’s Ark Lab
Efficient World Action Model Inference with Adaptive Intermediate States
Sep 28, 2026Zhinnan Liu, Haozhi Han, Ruge Zhang +8Efficient World-Action Model World Models
Xiamen University · Institute for AI Industry Research, Tsinghua University · School of Computer Science, Peking University +2

Oct 7, 2026, cs.ROJ/K move · Enter open · S save

RealtimeWAM: How Fast Can I Run My World Action Model?

Huanan Liu, Ye Li, Kangye Ji, Xiaoyu Chen+7

Tsinghua University · YuanxingGuangnian Robotics · Nanjing University

Open paper AskPDF arXiv

World Action Models (WAMs) combine visual dynamics modeling with action generation, but their high inference latency limits responsive robot control. Recent efforts accelerate inference by removing explicit future-video generation at test time, as in FastWAM, an approach that requires a specially tailored architectural design. More general caching strategies exploit feature redundancy, but redundancy alone does not capture the changing computational demands of closed-loop control. To address these challenges, we present RealtimeWAM, a general, training-free framework that coordinates parallel execution with adaptive computation for low-latency inference across diverse WAM architectures. We exploit layerwise dependencies to overlap observation processing with prediction. However, concurrent branches still compete for GPU resources, limiting the benefit of parallel execution. We therefore adapt computation throughout the pipeline through selective reuse, caching observation features in visually stable regions and reusing Transformer residuals while reserving additional refinement for small predicted adjustments. We evaluate RealtimeWAM on FastWAM and OpenWAM across RoboTwin, LIBERO, and LIBERO-Plus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90

\times

and 10.67

\times

. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM, respectively.

Abstract

Explore similar work

RealtimeWAM: How Fast Can I Run My World Action Model?

Faster-WAM: Do World Action Models Need Deep Action Modules?

Efficient World Action Model Inference with Adaptive Intermediate States