architecture · first seen 6 Oct 2026
Mixture-of-Transformers
Also: MoT
A transformer design that uses modality-specific parameters while sharing global self-attention across tokens.
Mentions per week
PapersCodeDiscussion
Earliest sources
- 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,…
- Video Prediction Policy 2: Predict Better, Act BetterPapers · 7 Oct 2026 · Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang, Qingyuan Yang, Qingzhou L…
- PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action PoliciesPapers · 8 Oct 2026 · Yu Liu, Hetian Guo, Tianlv Huang, Ziyi Cai, Wudi Chen, Hantang Wang, Qiutong Liu…
- BridgeWAM: Bridging Video and Action Experts via Latent Bridge QueriesPapers · 10 Oct 2026 · Jiaxin Fang, Ruitong Liu, Zeyu Lai, Xingyu Wang, Mingyuan Jia, Pingyue Sheng, We…
- DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous DrivingPapers · 13 Oct 2026 · Shuzheng Wang, Haoxuan Li, Shengzhen Li, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Li…
- Perceive, Predict, and Plan: a Unified World Action Model for Egocentric Dexterous ManipulationPapers · 15 Oct 2026 · Zirui Wu, Chen Guo, Tianjian Jiang, Zeren Jiang, Zeming Li, Lingchen Yang, Longt…
Latest sources
- 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…
- WeLM-Image: A Unified Image Generation Model towards Visual IntelligencePapers · 5 Nov 2026 · Canmiao Fu, Chen Li, Guohui Zhang, Hao Lu, Hongyang Wei, Huadong Wu, Huaisong Zh…
- WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale PretrainingPapers · 29 Oct 2026 · Yuhao Lu, Jiongxu Chen, Hexiang Wei, Jiajin Wu, Juelin Li, Mingjian Liang, Fan Y…
- Trace-WAM: Learning to Act via 3D Motion Prediction for World Action ModelsPapers · 27 Oct 2026 · Xu Hu, Changjie Wu, Linzhe Shi, Hang Zhang, Chen Yang, Lingjun Zhang, Guowen Zha…
- Agentic World Action ModelsPapers · 21 Oct 2026 · Zhuoyang Liu, Dantong Niu, Botong Zhang, Boning Shao, Jing Wang, Ruijie Zheng, Y…
- Perceive, Predict, and Plan: a Unified World Action Model for Egocentric Dexterous ManipulationPapers · 15 Oct 2026 · Zirui Wu, Chen Guo, Tianjian Jiang, Zeren Jiang, Zeming Li, Lingchen Yang, Longt…
- DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous DrivingPapers · 13 Oct 2026 · Shuzheng Wang, Haoxuan Li, Shengzhen Li, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Li…
- BridgeWAM: Bridging Video and Action Experts via Latent Bridge QueriesPapers · 10 Oct 2026 · Jiaxin Fang, Ruitong Liu, Zeyu Lai, Xingyu Wang, Mingyuan Jia, Pingyue Sheng, We…
- PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action PoliciesPapers · 8 Oct 2026 · Yu Liu, Hetian Guo, Tianlv Huang, Ziyi Cai, Wudi Chen, Hantang Wang, Qiutong Liu…
- Video Prediction Policy 2: Predict Better, Act BetterPapers · 7 Oct 2026 · Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang, Qingyuan Yang, Qingzhou L…
- 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,…