1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation

Rundong Su; Pengtao Chen; Haohan Geng; Sha Zhang; Zhihang Yuan; Yicheng Rong; Chong Yu; Hao Huang

cs.CVOct 11, 2026

1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation

Authors: Rundong Su, Pengtao Chen, Haohan Geng, Sha Zhang, Zhihang Yuan, Yicheng Rong, Chong Yu, Hao Huang,

Organizations: Fudan University · University of Science and Technology of China · Peking University · Shanghai Innovation Institute

Abstract

World Action Models (WAMs) unify visual world modeling and action generation, yet their real-world deployment is heavily bottlenecked by iterative action denoising and the sequential execution of visual prefilling and action prediction. We demonstrate that the action-denoising trajectories in WAMs are approximately straight, rendering the first-step velocity a strong estimate of the final action direction. Building on this observation, we introduce 1Step-WAM, a framework that transforms multi-step action denoising into one single forward. Specifically, we employ a lightweight calibrator to directly correct the first step velocity, and use bandwidth-constrained action decoding to further reduce errors in the calibrated one-step actions. Compressing action generation into a single step enables it to execute in parallel with visual prefilling, completely breaking the sequential bottleneck of the traditional imagination-then-action paradigm. Evaluations on RoboTwin and LIBERO show that 1Step-WAM largely preserves multi-step task success with only about 13.4M trainable parameters, while achieving inference speedups of $7.44\times$ , $5.98\times$ , and $24.84\times$ for FastWAM, ImageWAM and Kairos, respectively. Furthermore, real-world robotic deployments using the FastWAM backbone confirm a consistent 7.44 $\times$ speedup while maintaining close success rate to the multi-step baseline. Code is avaliable at https://github.com/changdong1687/1Step-WAM.

Figures & tables

Figure 1: Speedups of 1Step-WAM over the original multi-step FastWAM, ImageWAM, and Kairos.

Figure 2: Overview of 1Step-WAM. It combines lightweight velocity calibration, bandwidth-constrained action decoding, and joint execution of video prefill for faster action generation.

Model	Method	Train params.	Clean	Random	Avg.	Latency (ms) $\downarrow$	Speedup $\uparrow$
FastWAM ( Yuan et al., 2026 )	Original	–	91.88	91.78	91.83	669.54	$1.00\times$
	Naive 1-Step	–	69.92	67.52	68.72	147.62	$4.54\times$
	DMD2 ( Yin et al., 2024a )	2.04B	82.48	83.40	82.94	147.62	$4.54\times$
	SnapFlow Luan et al. (2026)	1.02B	90.52	86.96	88.74	147.69	$4.53\times$
	Flash-WAM Akbari et al. (2026)	1.02B	90.44	89.80	90.12	147.62	$4.54\times$
	Ours (1Step-WAM)	13.42M	91.10	90.68	90.89	89.95	7.44 $\times$

Table 1: Evaluation result on RoboTwin ( Chen et al., 2025 ) simulation benchmark

Model	Method	Spatial	Object	Goal	Long	Mean
FastWAM ( Yuan et al., 2026 )	Original	97.8	99.8	96.0	96.0	97.4
	Naive 1-Step	97.0	99.2	95.0	91.6	95.7
	Ours (1Step-WAM)	97.4	99.2	95.4	94.2	96.6
ImageWAM ( Zhang et al., 2026 )	Original	97.2	99.2	98.8	98.4	98.4
	Naive 1-Step	95.8	99.6	97.2	94.6	96.8
	Ours (1Step-WAM)	97.6	100.0	98.2	96.8	98.2

Table 2: Success rates (%) on the LIBERO suites.

Figure 3: Real-world execution comparison on Stack Cups. In the illustrated rollouts, original FastWAM and 1Step-WAM successfully stack the cups, while naive 1-step fails.

Method	Pick Place	Stack Cups	Hang Mug	Avg.
Original FastWAM	100	90	50	80
Naive 1-Step	100	40	10	50
1Step-WAM	100	80	45	75

Table 3: Real World Tasks success rates (%)

Figure 4: Left: cosine similarity between velocities predicted at adjacent denoising steps. Right: the

\ell_{2}

magnitude of the predicted velocity at each step.

Model	Method	$K$	Clean	Randomized
FastWAM	Ours	8	$89.64\rightarrow\mathbf{91.10}$	$88.74\rightarrow\mathbf{90.68}$
	DMD2 ( Yin et al., 2024a )	8	$82.48\rightarrow\mathbf{84.08}$	$83.40\rightarrow\mathbf{83.60}$
	SnapFlow ( Luan et al., 2026 )	8	$90.52\rightarrow\mathbf{91.32}$	$86.96\rightarrow\mathbf{91.36}$
	Flash-WAM ( Akbari et al., 2026 )	8	$90.44\rightarrow\mathbf{91.08}$	$89.80\rightarrow\mathbf{91.00}$
ImageWAM	Ours	4	$91.56\rightarrow\mathbf{92.26}$	$91.72\rightarrow\mathbf{92.62}$
Kairos	Ours	8	$94.76\rightarrow\mathbf{96.56}$	$92.24\rightarrow\mathbf{93.84}$

Table 4: Ablation of bandwidth-constrained action decoding on RoboTwin retaining first

K

modes

Model	w/o Joint (ms) $\downarrow$	w/ Joint (ms) $\downarrow$	Speedup $\uparrow$	Reduction (%) $\uparrow$
FastWAM ( Yuan et al., 2026 )	149.05	89.95	$1.66\times$	39.65
ImageWAM ( Zhang et al., 2026 )	77.64	51.28	$1.51\times$	33.95
Kairos ( Team et al., 2026 )	134.78	73.73	$1.83\times$	45.30

Table 5: Ablation of joint video–action execution. “w/o joint execution” denotes naive sequential execution , whereas “w/ joint execution” uses the proposed joint execution schedule.

Figure 5: Per-joint temporal DCT coefficients of FastWAM teacher actions (blue) and teacher-minus-prediction residuals from the calibrated one-step model (red). Each panel corresponds to one continuous joint dimension, with frequency increasing along the horizontal axis.

Figure 6: Real-world execution comparison on pick place. In the illustrated rollouts, both are success.

Figure 7: Real-world execution comparison on hang mug. In the illustrated rollouts, original FastWAM and 1Step-WAM successfully hang mug, while naive 1-step fails.

Figure 8: Left: cosine similarity between velocities predicted at adjacent denoising steps. Right: the

\ell_{2}

magnitude of the predicted velocity at each step.

Figure 9: Left: cosine similarity between velocities predicted at adjacent denoising steps. Right: the

\ell_{2}

magnitude of the predicted velocity at each step.

Task	Fast-WAM				ImageWAM				Kairos
	Clean		Rand.		Clean		Rand.		Clean		Rand.
	Original	Ours	Original	Ours	10-steps	Ours	10-steps	Ours	Original	Ours	Original	Ours
adjust_bottle	1.00	1.0	1.00	0.99	1.00	1.0	0.99	0.99	1.0	1.0	1.0	1.0
beat_block_hammer	0.99	1.0	0.97	0.98	1.00	0.98	0.99	0.9	1.0	1.0	0.98	1.0
blocks_ranking_rgb	1.00	1.0	1.00	0.98	0.99	0.9	0.99	0.98	1.0	1.0	1.0	1.0
blocks_ranking_size	0.94	0.91	0.98	0.92	0.95	0.9	0.98	0.96	1.0	1.0	0.92	0.96

Table 6: Comparison of Fast-WAM, ImageWAM, and Kairos across manipulation tasks.

Efficient Inference for World Action Models

Efficient inference for world action models cuts the cost of predicting action-conditioned futures for responsive control and planning.

See all 80 papers

RealtimeWAM: One-Step Asynchronous World Action Models
Oct 5, 2026Chengtao Lv, Jinyang Du, Shuyi Feng +7Efficient Inference for World Action Models Robotic Manipulation
Nanyang Technological University · Beihang University · Sensetime +1
AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
Sep 27, 2026Rui Wang, Xiangyu Wang, Donglin Yang +4Adaptive Inference Diffusion Model Distillation
Southern University of Science and Technology · Shenzhen Loop Area Institute · The University of Hong Kong
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
Jun 17, 2026Yuyang Zhang, Wenyao Zhang, Zekun Qi +7Action-Conditioned World Models World Action Models
Shanghai Jiao Tong University · Tsinghua University · Tencent Robotics X +1

Oct 5, 2026J/K move · Enter open · S save

RealtimeWAM: One-Step Asynchronous World Action Models

Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong+6

Nanyang Technological University · Beihang University · Sensetime+1

Efficient Inference for World Action Models Robotic Manipulation Consistency Distillation World Action Models

Open paper AskPDF arXiv

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-expert iteration (\ie, multi-step action denoising) and inter-expert waiting (\ie, sequential execution of the video and action experts) still limit inference efficiency. To this end, we present RealtimeWAM, an extremely efficient WAM variant with one-step action generation and asynchronous inference, addressing these two bottlenecks. To reduce intra-expert iteration, we propose Teacher-Anchored Consistency Distillation (TACD) to address a local-global error gap: low local consistency error alone does not guarantee accurate final actions. TACD supplements local consistency with explicit supervision from the frozen teacher's multi-step rollout endpoint, enabling accurate one-step action generation. Additionally, we propose Cross-Expert Wavefront Pipelining (CEWP) to eliminate unnecessary expert-level waiting. It overlaps the two experts through block-wise sharing of the video KV cache, synchronizing only immediately before the corresponding action attention consumes it. Extensive experiments across diverse benchmarks (\eg, LIBERO, LIBERO-Plus and RoboTwin) and model variants (\eg, Fast-WAM and Faster-WAM) demonstrate the superiority of RealtimeWAM. Notably, RealtimeWAM maintains near-lossless performance (\ie,

<1\%

drop) across these benchmarks while delivering significant end-to-end speedup (\eg,

\sim25\times

on H100). Our code and checkpoints are available via this link.

Abstract

Efficient Inference for World Action Models

Explore similar work

RealtimeWAM: One-Step Asynchronous World Action Models

AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?