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

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 \textbf{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 (4)

• 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.
• 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.
• 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.