GigaWorld-Policy: An Efficient Action-Centered World--Action Model

Abstract

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0.

Figures (10)

• Figure 1: Comparison of GigaWorld-Policy with baselines on inference frequency and task success rate in real-world settings and on an A100 GPU.
• Figure 2: (a) VLM-based VLA with auxiliary future supervision to densify training signals, but limited by the discriminative nature of VLMs worldvladreamvlaswiftvla. (b) Joint action--video prediction with bidirectional attention motuscosmospolicyshen2025videovla, requiring future video generation at inference. (c) Two-stage design mimicvideo that first generates future video and then gets actions via an Inverse Dynamics Model (IDM), inheriting video prediction errors and incurring additional inference cost. (d) GigaWorld-Policy: an action-centered WAM that leverages future visual dynamics as supervision during training, while making future-video prediction optional at inference for low-latency action generation.
• Figure 3: Overview of GigaWorld-Policy, built on a pre-trained video generation backbone. During pre-training, the model learns action-relevant representations from large-scale videos. During post-training for policy learning, it jointly performs action-chunk prediction from the current observation and future video prediction as auxiliary supervision. At inference time, the future-video prediction branch is optional, enabling faster inference.
• Figure 4: Attention mask for GigaWorld-Policy: action tokens $T_{a}$ attend to states $T_{s}$ and current observations $T_{o}$ only, while future video tokens $T_{f}$ also attend to actions.
• Figure 5: Real-world deployment of GigaWorld-Policy on PiPER arms for QR code scanning.