[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-zero-shot-generalization":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"28646460-cb02-4b80-863b-25505ee186f9","zero-shot generalization","zero-shot-generalization",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"99ae4e8c-3fb2-4d46-8965-458bd16372c8","steerable-vi-vision-representations-zh","可被文字操控的 ViT 特徵","這篇論文把文字提示塞進 ViT 編碼過程中，讓影像特徵能朝指定物件偏移，同時盡量保留通用視覺用途。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775196412799-wufk.png","zh","2026-04-03T06:06:34.443487+00:00"]