SkyReg is introduced, a dataset and standardized benchmark for pixel-level drone-to-satellite geo-registration, providing dense per-pixel geo-location supervision across diverse settings (orthographic and perspective), scene types, and camera configurations.
Qingyang Liu, D. Shatwell, P. Kulkarni et al.· 0 citations
X-GeoP2P, a coarse-to-fine localization pipeline that combines adapted versions of GAReT and X-VGGT, is presented, a coarse-to-fine localization pipeline that combines adapted versions of GAReT and X-VGGT.
Wyatt Petula, Soumik Ghosh, Qingyang Liu et al.· 0 citations
Mean Cumulative Drift (MCD), an embedding-based measure of content retention across three representation spaces, and Multi-Generation GenEval (MGG), extending GenEval's object-level compliance scoring across generations are proposed, to quantify drift.
Inspired by render-based compression, this work renders textual chains of thought into images, extract visual features, and construct a discrete latent vocabulary via clustering-based fine-tuning, and concludes that discrete latent tokens provide a controllable and interpretable basis for efficient latent reasoning.
Shuochen Chang, Qingyang Liu, Shaobo Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.