arXiv:2607. 24112v1 Announce Type: new Abstract: We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents.
By Xiangyan Liu, Kaixin Li, Haonan Wang, Biao Wu, Meng Fang, Longxu Dou, Chao Du, Michael Qizhe Shieh, Tianyu Pang
arXiv:2606. 14801v1 Announce Type: cross Abstract: Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult.
By Yifan Ruan, Chenyang Cao, Andreas Burger, Ali Pesaranghader, Kaveh Kamali, Jaehong Kim, Nandita Vijaykumar, Alan Aspuru-Guzik, Igor Gilitschenski, Nicholas Rhinehart
arXiv:2608. 05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL).
By Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state transitions by jointly optimizing inverse dynamics (predicting actions from state changes) and forward dynamics (predicting next states from current states and actions).
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction).
arXiv:2606. 29705v1 Announce Type: new Abstract: Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models.
By Sunqi Fan, Lingshan Chen, Runqi Yin, Qingle Liu, Yongming Rao, Meng-Hao Guo, Shi-Min Hu