GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

GigaWorld Team Angen Ye Ang-Yuan Ma Boyuan Wang Chaojun Ni Fangzheng Ye Guan Huang Guo Li Guosheng Zhao Hao-Dong Yan Heng-Tao Li Jiwen Lu Kai Wang Mingming Yu Qitang Hu Qiuping Deng Song-Lin Liu Xiaoyu Tian Xiao-Feng Wang Xinyu Zhou Xiu-Wei Xu Xinze Chen Yang Wang Yejun Zeng Yifan Chang Yun Ye Zhenyu Wu Zhan-Qian Wu Zheng Zhu

Jul 2026 · arXiv.org · Vol abs/2607.13960 · 3 citations · 67 references

Computer Science

TL;DR

GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control, and introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.

Abstract

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual dynamics are used during training while action-only decoding is used at inference time. Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control. During pretraining, GigaWorld-Policy-0.5 adopts a mixed Action-Conditioned World Modeling (AC-WM) and WAM training strategy. This strengthens the coupling between visual dynamics and robot actions and improves the transferability of action representations for downstream policy learning. For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts, reducing active computation during action-only inference and achieving 85 ms inference latency on a local RTX 4090 setup. In addition, we employ an agent-based AutoResearch pipeline to systematically search training configurations, enabling more efficient identification of optimal experimental setups while reducing the time and manual intervention required for hyperparameter tuning. Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.

DOI arXiv Semantic Scholar

View source

Similar papers

Preprint Aug 2026

WAM-OPD: On-Policy Distillation for World Action Models

WAM-OPD, a deployment-consistent post-training recipe for a video-first WAM, is introduced and it is suggested that dense teacher supervision on student-induced histories is a promising post-training interface for video-first WAMs.

Liu Yang, Zhuang Jiang, Chenchao Sheng et al. · 1 citation

Preprint Aug 2026

JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor, predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, while preserving dense patch-level correspondence.

Yihan Lin, Jiawei He, Shifeng Bao et al. · 4 citations · ⚡1

Preprint Aug 2026

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal, co-trains a pretrained video expert and a lightweight action expert with joint flow matching and applies reinforcement learning to optimize a compositional driving reward beyond trajectory imitation.

Zongchuang Zhao, Xin Zhou, Tianyang Xu et al. · 1 citation · ⚡1

Preprint Aug 2026

SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation

SLIM (Self-supervised Latent Interaction Model), a compact 0.5B-parameter latent interaction policy, which matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters, no additional embodied pretraining, lower inference latency, and substantially lower GPU memory usage.

Jingkai Wang, Zihan Tang, Gu Zhang et al. · 0 citations

Preprint Aug 2026

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

World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substantial latency. Fast-WAM removes this process for efficiency; however, our matched implementations show lower generalization for Fast-WAM than for future-aware alternatives, especially with scarce robot demonstrations and in out-of-distribution scenarios. To bridge this gap, we introduce **LAWA**, a WAM architecture that uses compact latent actions as an operational representation of future intentions, enabling efficient test-time future imagination without generating future observations. Specifically, a discrete tokenizer enhanced by action-free pre-training produces manipulation-centric codebook targets. LAWA jointly denoises a continuous latent state anchored to these targets with executable action chunks while omitting the future-video branch at inference. On RoboCasa, LAWA achieves state-of-the-art average success rates of 65.6% and 80.8% in the few-shot and full data settings, improving over the matched Fast-WAM baseline by 9.6 and 4.5 points, respectively. It also preserves the performance level of the matched Joint-WAM variant while requiring 42.9% lower inference latency. LAWA also demonstrates competitive zero-shot robustness on LIBERO-Plus and superior performance on real-world tasks. These results show that future imagination need not be discarded: retaining it with compact latent actions yields an effective trade-off among performance, generalization, and latency. Code and models will be released.

Xiang Li, Yupeng Zheng, Song-En Gu et al. · 1 citation · ⚡1

Preprint Aug 2026

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

Faster-WAM introduces a sparse future-conditioning framework that computes future representations once and selectively reuses them throughout action denoising, and proposes SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fusion to aggregate multi-depth future representations without increasing attention complexity.

Weiheng Zhao, Haoyi Jiang, Xin Shi et al. · 4 citations