TTRSD separates update direction from update position, determined by group-relative advantages, from update position, determined by visual sensitivity, without requiring ground-truth labels, external verifiers, or a separate teacher, demonstrating cross-dataset generalization while preserving inherent reasoning integri...
Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an image, a task instruction, and a runtime candidate set to a structured choice and candidate-conditioned probabilities using small open multimodal mod...
Xun-Lan Zhou, Xian-Liang Yang, Li Zhao· arXiv.org· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.