model · first seen 4 Oct 2026
world action model
Also: WAM, world models for robotics, world models for robot learning, video diffusion model for robot control
Models that jointly forecast future scenes and ego trajectories to support planning in autonomous driving.
World Action Models (WAMs) are policies, mostly for robotic manipulation and also for autonomous driving, that jointly predict future observations and actions, often built on pretrained video diffusion or flow-matching backbones. Recent papers treat WAM as a named paradigm and work on its practical problems: inference cost (RealtimeWAM, Elastic-WAM, Bind-WAM, a caching study on the 6B Fast-WAM), action-consistency of predicted futures (R^2-WAM), recovery from execution drift, and focusing supervision on what changes (ResWAM, DiffWAM). A driving benchmark tests hazard reaction in WAMs and VLAs. Code releases come from several groups, including DexForce's 3D-native Unitas and THUSI-Lab's PrismWAM.
If predicting the visual future alongside actions keeps beating plain vision-language-action policies, video generation backbones could become the default foundation for robot policies. The heavy focus on efficiency suggests that inference cost is the main obstacle to running them on real robots.
Analyst note (emerging), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 16 on 16 Nov 2026 · 52 mentions in 28 days · 52 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.05
Earliest sources
- $R^2$-WAM: Repair-and-Reject Post-Training for World Action ModelsPapers · 4 Oct 2026 · Ruiyan Xu, Haisheng Su, Sixu Lin, Zhaokun Yue, Chengming Hu, Xin Jin, Guiliang L…
- ZhuoyangLiu2005/agentic-wamCode · 4 Oct 2026 · ZhuoyangLiu2005 · 178 stars
- Future Anchored Verification and Online Recovery for World Action ModelsPapers · 5 Oct 2026 · Zhibin Qin, Zhenxiong Tan, Xinchao Wang
- RealtimeWAM: One-Step Asynchronous World Action ModelsPapers · 5 Oct 2026 · Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong, Shiqiao Gu, Shunzi Yang, Ruihao…
- TAPDreamer: Transferable Adversarial Patches for World Action ModelsPapers · 5 Oct 2026 · Xuanyu Lu, Fengqing Jiang, Kaiyuan Zheng, Yichen Feng, Yaorui Ding, Yuetai Li, Z…
- OpenWAM: An Open Framework for Composable World-Action ModelsPapers · 6 Oct 2026 · Heng Yu, David D. Yuan, Juze Zhang, Changan Chen, Yao Feng, Michelle Baldonado,…
Latest sources
- ThinkWAM: Rethinking Latent Futures for Action RefinementPapers · 16 Nov 2026 · Haoyun Tang, Baqiao Deng, Enjin Zhou, Songwen Tian, Keyao Xu, Bowen Jing, Kun Wa…
- ReactBench-AD: Do Driving VLAs and World-Action Models React to Imminent Hazards in Their Path?Papers · 15 Nov 2026 · Nikos Theodoridis, Reenu Mohandas, Sushil Sharma, Ciarán Hogan, Ganesh Sistu, A…
- DiffWAM: Learning World Action Model from Consecutive Visual DifferencePapers · 15 Nov 2026 · Xinheng Zhang, Haoyu Xiong, Chao Jing, Xiaohan Zhang, Linshan Li, Hongbang Fan,…
- Cache or Denoise Less? Residual Reuse in a Flow-Matching World Action ModelPapers · 15 Nov 2026 · Abhinav Gupta, Nissan Pow
- ResWAM: Learning What Changes, Not What Stays, for World-Action ModelsPapers · 14 Nov 2026 · Chongyu Fan, Gaowen Liu, Ramana Rao Kompella, Jason Corso, Sijia Liu
- Bind-WAM: Binding-Uncertainty-Guided Selective Future Imagination in World Action ModelsPapers · 11 Nov 2026 · Chenhao Qiu, Shuyi Chen, Songen Gu, Shufeng Nan, Tianyu Wang, Siyu Lin, Yifan Li…
- From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action ModelsPapers · 10 Nov 2026 · Guoqiang Liang, Yiqi Lin, Yanzhe Chen, Kevin Yuchen Ma, Mike Zheng Shou
- Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot ControlPapers · 10 Nov 2026 · Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xia…
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent ReasoningPapers · 10 Nov 2026 · Xuheng Zhang, Yiming Zhang, Jialin Gao, Hao Chen, Jiaming Liu, Ji Li, Runzhong H…
- WAM is capable in BEHAVIOR-1K: the 2nd-place solution to the 2026 BEHAVIOR ChallengePapers · 10 Nov 2026 · Yelin He, Jiaquan Ye, Xinming Wei, Wenjie Xiao, Gengming Zhang, Guoting Wei, Xia…
- SWAM: Scaling World Action Models with Cross-Modal AlignmentPapers · 9 Nov 2026 · Yu Zhou, Xinyuan Xia, Xuankun Yang, Yinghao Yang, Wendi Chen, Bowen Liu, Jianhan…
- ForeAct: Geometry-Guided Action Learning from World RepresentationsPapers · 8 Nov 2026 · Wei Lu, Jiaxi Zhang, Yunheng Wang, Taowen Wang, Yuetong Fang, Zhenhui Zhang, Shu…
Mentioned together with
In the ledger
- 2026-W47 · baseline #7 · open