Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Tianyuan Yuan; Zibin Dong; Yicheng Liu; Hang Zhao

cs.CVMar 17, 2026

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Authors: Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao

Organizations: IIIS, Tsinghua University · Galaxea AI

Abstract

World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an imagine-then-execute paradigm, incurring substantial test-time latency from iterative video denoising, yet it remains unclear whether explicit future imagination is actually necessary for strong action performance. In this paper, we ask whether WAMs need explicit future imagination at test time, or whether their benefit comes primarily from video modeling during training. We disentangle the role of video modeling during training from explicit future generation during inference by proposing Fast-WAM, a WAM architecture that retains video co-training during training but skips future prediction at test time. We further instantiate several Fast-WAM variants to enable a controlled comparison of these two factors. Across these variants, we find that Fast-WAM remains competitive with imagine-then-execute variants, while removing video co-training causes a much larger performance drop. Empirically, Fast-WAM achieves competitive results with state-of-the-art methods both on simulation benchmarks (LIBERO and RoboTwin) and real-world tasks, without embodied pretraining. It runs in real time with 190ms latency, over 4 $\times$ faster than existing imagine-then-execute WAMs. These results suggest that the main value of video prediction in WAMs may lie in improving world representations during training rather than generating future observations at test time. Project page: https://yuantianyuan01.github.io/FastWAM/

Figures & tables

Figure 1: Three representative WAM paradigms. (A) Joint-modeling WAMs denoise future video and action tokens together. (B) Causal WAMs first generate future observations and then condition action prediction on the generated future representation. (C) Fast-WAM retains video co-training during training but removes explicit future generation at inference time, directly predicting actions from latent world representations in a single forward pass.

Panel of Figure 2 — Figure 2: Fast-WAM architecture and the structured attention mask used to disentangle video co-training from action generation.

Figure 3: Real-world towel-folding task on the Galaxea R1 Lite platform. Folding a deformable object requires long-horizon planning and precise closed-loop manipulation, making it a challenging benchmark for evaluating both task success and execution efficiency.

Method	Embodied PT.	Clean	Rand.	Average
$\pi_{0}$ [ 10 ]	✓	65.92	58.40	62.2
$\pi_{0.5}$ [ 11 ]	✓	82.74	76.76	79.8
Motus [ 5 ]	✓	88.66	87.02	87.8
Motus from WAN2.2	✗	77.56	77.00	77.3
LingBot-VA [ 3 ]	✓	92.90	91.50	92.2
LingBot-VA from WAN2.2	✗	80.60	–	80.6

Table 1: Results on RoboTwin. Fast-WAM matches strong pretrained WAM baselines without using embodied pretraining, while the two imagine-then-execute variants remain highly comparable and removing video co-training causes a substantial drop.

Method	Embodied PT.	Spatial	Object	Goal	Long	Average
OpenVLA [ 9 ]	✓	84.7	88.4	79.2	53.7	76.5
$\pi_{0}$ [ 10 ]	✓	96.8	98.8	95.8	85.2	94.1
$\pi_{0.5}$ [ 11 ]	✓	98.8	98.2	98.0	92.4	96.9
LingBot-VA [ 3 ]	✓	98.5	99.6	97.2	98.5	98.5
Motus [ 5 ]	✓	96.8	99.8	96.6	97.6	97.7
Fast-WAM (Ours)	✗	98.2	100.0	97.0	95.2	97.6

Table 2: Results on LIBERO. Fast-WAM achieves competitive overall performance without embodied pretraining, remains close to both imagine-then-execute variants, and outperforms the no-video-co-training ablation by a clear margin.

Figure 4: Real-world results on the long-horizon towel-folding task. The left panel plots success rate against average completion time, where upper-left is better. The right panel compares inference latency. Fast-WAM achieves strong real-world performance with substantially lower latency than imagine-then-execute variants, while removing video co-training degrades both success rate and completion time.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Task	Fast-WAM (Ours)		Fast-WAM-Joint		Fast-WAM-IDM		Fast-WAM w.o. co-train		LingBot-VA		$\pi_{0.5}$		Motus
	Clean	Rand.	Clean	Rand.	Clean	Rand.	Clean	Rand.	Clean	Rand.	Clean	Rand.	Clean	Rand.
Adjust Bottle	100	100	98	99	94	99	98	100	90	94	100	99	89	93
Beat Block Hammer	99	97	100	98	98	98	80	92	96	98	96	93	95	88
Blocks Ranking RGB	100	100	100	100	100	99	88	86	99	98	92	85	99	97
Blocks Ranking Size	94	98	83	91	79	90	56	62	94	96	49	26	75	63
Click Alarmclock	100	100	100	100	98	100	100	98	99	100	98	89	100	100

Appendix

Table 3: Per-task success rates on RoboTwin under clean and randomized evaluation settings.

World Action Models

World Action Models connect predictions of how scenes change under action to executable policies for robots, vehicles, and other embodied agents.

See all 206 papers

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
Jun 8, 2026Jiajun Li, Tiecheng Guo, Yifan Ye +9World Models for Robotics Efficient Inference for World Action Models
1The University of Hong Kong · 2Peking University · 3Muka Robotics +2
Latent Action as Intention Enables Efficient Future Imagination for World Action Models
Aug 25, 2026Xiang Li, Yupeng Zheng, Songen Gu +11Latent Action Learning World Models for Robotics
1CollegeAI, THU · 2AIR, THU · 4TARS Robotics +6
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

Jun 8, 2026J/K move · Enter open · S save

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination

Jiajun Li, Tiecheng Guo, Yifan Ye, Rongyu Zhang+8

1The University of Hong Kong · 2Peking University · 3Muka Robotics+2

World Models for Robotics Efficient Inference for World Action Models Robotic Manipulation World Action Models Diffusion Model Inference Acceleration Video World Models

Open paper AskPDF arXiv

World-Action Models (WAMs) have emerged as a promising paradigm for embodied control by coupling future visual prediction with action generation. However, most existing WAMs rely on photorealistic future prediction, which incurs high inference latency and makes real-time robot deployment difficult. This motivates a more efficient WAM design that preserves the control benefits of future visual prediction while reducing its inference cost. We introduce Efficient-WAM, a World-Action Model that reduces the cost of future imagination while preserving its control benefit. Efficient-WAM improves inference efficiency via a compact video expert transferred from WAN-2.2-5B, token-sparse video latents, and asymmetric video-action denoising that allocates fewer sampling steps to video than to actions. Instead of optimizing the future branch for visual fidelity, Efficient-WAM treats future video prediction as a compact guidance signal for action generation. Comprehensive experiments on RoboTwin 2.0 and real-world manipulation tasks show that Efficient-WAM maintains strong action performance despite visibly coarse future predictions. While maintaining competitive control capabilities, our 1B-parameter model can reduce per-chunk latency to around 100 ms during physical deployment, achieving a 30x speedup over existing WAMs.

Abstract

World Action Models

Explore similar work

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination

Latent Action as Intention Enables Efficient Future Imagination for World Action Models

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