作者位次 #2/11ICML 2026Poster· Applications / Computer Vision
ViTok-v2: Scaling Native Resolution Autoencoders to 5 Billion Parameters
Philippe Hansen-Estruch · Jiahui Chen · Vivek Ramanujan · Orr Zohar · Markos Georgopoulos · Animesh Sinha · Ji Hou · Edgar Schönfeld · Felix Juefei-Xu · Sriram Vishwanath · Ali Thabet
多模态OpenReview