Recent advances in diffusion models have demonstrated remarkable generative capabilities, but their application to style transfer remains limited by inference instability and poor adaptation to diverse styles. Many methods either rely on costly fine-tuning or sacrifice flexibility and controllability at inference time....
Yan-Zhi Yuan, Zhi-Qiang Pan, Le Xia et al.· Applied Sciences· 0 citations
The results show that benchmark reliability in educational AI is constrained less by algorithm choice than by data structure, group heterogeneity, and evaluation design, and increasing model complexity did not remove this pattern: ensemble models improved structurally sound datasets but amplified instability or failed...
This paper asks what information wrong-consensus agreement actually contains, and answers with a quantitative decomposition, and contrasts near-complete mechanical agreement in the open-weights models against a larger preference-unexplained residual in the frontier family.
Li-Zhuo Zhang, Meng-Meng Tang, Chen-Feng Long et al.· 1 citation
AnchorScore provides a low-cost ranking signal that directs expensive MLLM evaluation to the classes where it is most informative, and three practical applications follow: a deployable hybrid CLIP/MLLM routing strategy, prompt disambiguation on hard classes (exploratory), and review-priority prediction for human verifi...
A quantitative account of the failure of majority voting over multiple LLM samples to raise answer accuracy, yet its gain varies erratically: on hard questions it can even backfire.
Lizhuo Zhang, Mengmeng Tang, Chenfeng Long 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.
