This work builds a synthetic data engine that leverages a spatio-temporal scene graph as a difficulty measure and casts difficulty-controlled query synthesis as a constraint programming problem, producing difficulty-graded data for both evaluation and training and proposes CurrSTVG, a curriculum reinforcement learning...
Xing-Jian Wang, Shi-Jian Wang, Yi-Bo Wang et al.· 0 citations
StreamMind is introduced, a two-tier architecture that assigns latency-critical interaction and proactive monitoring to independently scheduled frontend workers, while backend workers asynchronously construct persistent multimodal memory and perform historical recall and external search.
Xichen Zhang, Guankai Li, Yinghao Zhu et al.· 1 citation
This work introduces Harness-R1, the first method, to the authors' knowledge, that makes failure-conditioned, lifecycle-wide editing of an existing executable runtime a learned capability, and post-trains a dedicated harness engineer with online reinforcement learning so that its edits are optimized for the realized ta...
Shuai Shao, Kangning Zhang, Qingyao Li et al.· 10 citations· ⚡2
Method, an egocentric world-action simulator that synthesizes controllable, high-quality manipulation videos to expand scarce real-world training data, is presented, demonstrating that the synthesized data substantially improve downstream WAM generalization.
Zexuan Yan, Yuzhou Wu, Yue Ma et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
