[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-vision-transformers":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"aa7d0698-56a7-4b5b-b97c-240f377f6aab","vision transformers","vision-transformers",1,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"25495601-69d8-42fa-868d-ccd71c6d1347","outlier-tokens-diffusion-transformers-dsr-en","Outlier Tokens in DiTs, and How DSR Fixes Them","A new paper shows outlier tokens affect both RAE encoders and DiT denoisers, and proposes Dual-Stage Registers to reduce artifacts.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778134850923-gtbr.png","en","2026-05-07T06:20:32.854811+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"5db60597-3ab6-4c21-90ec-13fa9bd30bd6","steerable-vi-vision-representations-en","Steerable ViT Features for Text-Guided Vision","A new vision representation lets text steer ViT features toward specific objects without giving up generic visual utility.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775196409641-4e2e.png","2026-04-03T06:06:34.954101+00:00"]