This paper proposes PACE, a two-stage framework that progressively expands both the representation and trainable parameter spaces, and introduces Focal Embedding Loss, a confidence-adaptive objective that downweights queries with high positive retrieval confidence while emphasizing ambiguous queries with competitive ne...
Yan-Ping Li, Wei Zhou, Ya-Wen Liu et al.· 1 citation
This work proposes a novel framework, Search2Skill, that automatically identifies the agent's capability gaps, searches external sources to address them, and distills the retrieved evidence into structured, reusable skills.
Muyang Ye, Tian Lan, Feihu Jiang et al.· 1 citation
Credit-Aware Hierarchical Memory Evolution (CHIME), a self-evolving memory framework that maintains a separate planning bank and execution bank and follows an attribute-before-memorize principle, which shows that CHIME consistently outperforms state-of-the-art training-based and self-evolving memory baselines.
Yongshi Ye, Tian Lan, Feihu Jiang et al.· 0 citations
This work introduces OvisOCR2, a 0.8B document parsing model designed as an end-to-end parser that combines filtered real-document annotations with synthetic pages whose rendered images and Markdown targets are derived from the same HTML source.
Shiyin Lu, Yinglun Li, Yu Xia 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.