VIVAS is proposed, a framework built upon the unified token space paradigm, which introduces a dense-structural-semantic vision tokenizer, which expands the textual vocabulary into a unified vision-language vocabulary by incorporating a visual vocabulary.
Zhe-Han Kan, Yu-Bo Zhu, Xing-Hua Jiang et al.· 1 citation
UVU effectively synergizes pixel-level visual perception with semantic-level visual understanding, internalizing visual reconstruction capabilities and unlocking the facilitative role of visual supervision in enhancing understanding in the pre-training stage.
Zhe-Han Kan, Xing-Hua Jiang, Yu-Bo Zhu et al.· 1 citation
This work proposes SubJudge, a System One model for personalized scoring with Batchwise Preference Optimization (BPO), a pairwise comparative framework for multi-dimensional scale construction that combines sparse Elo comparisons with multi-judge voting and optimized both offline scale construction and online inference...
Xiang-Long Shi, Shi-Feng Liu, Si-Rui Zhao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.