This paper proposes MOCO, a novel diffusion-based framework capable of processing multiple simultaneous inputs, including speech audio, text descriptions, and trajectory data, to generate coherent and lifelike motions without requiring aligned multimodal data.
Yi-Fei Liu, Qiong Cao, Hong-Wei Yi et al.· European Conference on Compu...· 0 citations
SearchMaster is presented, a self-play framework that trains a single LLM from search tasks it generates, solves, and verifies in a local search environment, showing that grounded and regulated self-play can provide effective search-agent training data without human-labeled QA pairs or expert demonstrations.
Wentao Tan, Qiong Cao, Jia-Qi Wang et al.· 2 citations
A benchmark that evaluates whether LLM auditors can localize, attribute, and repair search-agent failures through evidence-grounded adjudication, and proposes SearchAuditor, a multi-perspective auditing framework that effectively localizes, attributes, and repairs search-agent failures through evidence-grounded adjudic...
Zhixiang Liang, Yifei Liu, Yi-Dan Huang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
