Episode

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

Podcast
Daily Paper Cast
Published
Jul 17, 2026
Duration seconds
1273
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/65d7b1a5
Audio
https://media.transistor.fm/65d7b1a5/9b65bb19.mp3
JSON
/v1/public/podcasts/daily-paper-cast-7079649/episodes/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch
Markdown
/podcast/daily-paper-cast-7079649/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/daily-paper-cast-7079649/gigaworld-policy-0-5-a-faster-and-stronger-wam-empowered-by-autoresearch.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

🤗 Upvotes: 23 | cs.RO Authors: GigaWorld Team, Angen Ye, Angyuan Ma, Boyuan Wang, Chaojun Ni, Fangzheng Ye, Guan Huang, Guo Li, Guosheng Zhao, Haodong Yan, Hengtao Li, Jiwen Lu, Kai Wang, Mingming Yu, Qitang Hu, Qiuping Deng, Songling Liu, Xiaoyu Tian, Xiaofeng Wang, Xinyu Zhou, Xiuwei Xu, Xinze Chen, Yang Wang, Yejun Zeng, Yifan Chang, Yun Ye, Zhenyu Wu, Zhanqian Wu, Zheng Zhu Title: GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch Arxiv: http://arxiv.org/abs/2607.13960v2 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 la…