Fangzhou Wu, Rikhav Shah, Sandeep Silwal, Qiuyi Zhang
In recent years, Muon has emerged as the dominant method for training large language models, and transformers more broadly. The essential difference, when compared to standard gradient descent…
cs.LGcs.NA
Théo Gigant, Bowen Peng, Jeffrey Quesnelle
Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work,…
cs.CLcs.LG
Kirscher Tristan, Bujotzek Markus, Kirchhoff Yannick, Rokuss Maximilian, Isensee Fabian
Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via K-fold cross-validation (CV), yet refer to them…
cs.LGcs.CV
Jinrang Jia, Zhenjia Li, Yijiang Hu, Yifeng Shi
Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single…
cs.CVcs.GR