\n","updatedAt":"2024-07-11T19:40:19.904Z","author":{"_id":"6141a88b3a0ec78603c9e784","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg","fullname":"merve","name":"merve","type":"user","isPro":true,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":9203}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6338393092155457},"editors":["merve"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg"],"reactions":[],"isReport":false}},{"id":"66903701a534fc4f3c22fdab","author":{"_id":"6184039c5259a19df59de7bc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6184039c5259a19df59de7bc/6B-cpdkoBttLozqlMyxJW.jpeg","fullname":"Jeremy Pinto","name":"jerpint","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":17},"createdAt":"2024-07-11T19:48:17.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"are the finetuned models going to be available on huggingface?","html":"
are the finetuned models going to be available on huggingface?
\n","updatedAt":"2024-07-11T19:48:17.425Z","author":{"_id":"6184039c5259a19df59de7bc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6184039c5259a19df59de7bc/6B-cpdkoBttLozqlMyxJW.jpeg","fullname":"Jeremy Pinto","name":"jerpint","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":17}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.94725501537323},"editors":["jerpint"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6184039c5259a19df59de7bc/6B-cpdkoBttLozqlMyxJW.jpeg"],"reactions":[],"isReport":false}},{"id":"66914a3f20dce959ab9d09e5","author":{"_id":"61c8cf95ccae6d3b4a6c006d","avatarUrl":"/avatars/caa852cececab6b5bc3f346845fa2a86.svg","fullname":"Yunus Serhat Bıçakçı","name":"yunusserhat","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":19},"createdAt":"2024-07-12T15:22:39.000Z","type":"comment","data":{"edited":true,"hidden":false,"latest":{"raw":"> are the finetuned models going to be available on huggingface?\n\nI think it is already available. \nhttps://huggingface.co/collections/google/paligemma-release-6643a9ffbf57de2ae0448dda\nhttps://huggingface.co/collections/google/paligemma-ft-models-6643b03efb769dad650d2dda","html":"
\n
are the finetuned models going to be available on huggingface?
\n","updatedAt":"2024-07-12T15:24:35.380Z","author":{"_id":"61c8cf95ccae6d3b4a6c006d","avatarUrl":"/avatars/caa852cececab6b5bc3f346845fa2a86.svg","fullname":"Yunus Serhat Bıçakçı","name":"yunusserhat","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":19}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.971986711025238},"editors":["yunusserhat"],"editorAvatarUrls":["/avatars/caa852cececab6b5bc3f346845fa2a86.svg"],"reactions":[{"reaction":"👍","users":["merve","osanseviero"],"count":2}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2407.07726","authors":[{"_id":"668f4967f65238b10c6b12b7","user":{"_id":"642d334ff65714b4585f2de4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642d334ff65714b4585f2de4/gxBynq5KyoUP0VlAQD3-w.jpeg","isPro":false,"fullname":"Lucas Beyer","user":"giffmana","type":"user"},"name":"Lucas Beyer","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:43:35.767Z","hidden":false},{"_id":"668f4967f65238b10c6b12b8","name":"Andreas Steiner","hidden":false},{"_id":"668f4967f65238b10c6b12b9","name":"André Susano Pinto","hidden":false},{"_id":"668f4967f65238b10c6b12ba","name":"Alexander Kolesnikov","hidden":false},{"_id":"668f4967f65238b10c6b12bb","name":"Xiao Wang","hidden":false},{"_id":"668f4967f65238b10c6b12bc","user":{"_id":"68d5c05805ddd80041f80776","avatarUrl":"/avatars/53a304076359f11cc92de22a2cfbec06.svg","isPro":false,"fullname":"Daniel Salz","user":"dasalz","type":"user"},"name":"Daniel Salz","status":"claimed_verified","statusLastChangedAt":"2025-09-26T12:30:24.393Z","hidden":false},{"_id":"668f4967f65238b10c6b12bd","user":{"_id":"65a9196f9fa2a0f9a2d27759","avatarUrl":"/avatars/fe274d04b2ff7d8a079cdde6a77395c4.svg","isPro":false,"fullname":"Maxim Neumann","user":"maximn","type":"user"},"name":"Maxim Neumann","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:46:01.880Z","hidden":false},{"_id":"668f4967f65238b10c6b12be","user":{"_id":"630545da20668afe24860235","avatarUrl":"/avatars/5d82be2e7412bff1af15cc5eafa60b7d.svg","isPro":false,"fullname":"Ibrahim Alabdulmohsin","user":"ibomohsin","type":"user"},"name":"Ibrahim Alabdulmohsin","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:46:09.539Z","hidden":false},{"_id":"668f4967f65238b10c6b12bf","user":{"_id":"6489893e1ec8356ba5bb9777","avatarUrl":"/avatars/54354c1e5774cadd1d83d42054e9d96b.svg","isPro":false,"fullname":"Michael Tschannen","user":"mitsch","type":"user"},"name":"Michael Tschannen","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:46:36.803Z","hidden":false},{"_id":"668f4967f65238b10c6b12c0","user":{"_id":"626a9284783d5891f45beb53","avatarUrl":"/avatars/8737662babc5d42cafba6087ab33e716.svg","isPro":false,"fullname":"Emanuele Bugliarello","user":"e-bug","type":"user"},"name":"Emanuele Bugliarello","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:46:45.351Z","hidden":false},{"_id":"668f4967f65238b10c6b12c1","name":"Thomas Unterthiner","hidden":false},{"_id":"668f4967f65238b10c6b12c2","user":{"_id":"662fc73ccee11621a1067db1","avatarUrl":"/avatars/4fbfbc0621f631d8e95a2a642fa0cd27.svg","isPro":false,"fullname":"Daniel Keysers","user":"dkeysers","type":"user"},"name":"Daniel Keysers","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:47:05.769Z","hidden":false},{"_id":"668f4967f65238b10c6b12c3","user":{"_id":"65451016321f0393f453cd7b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/XBmF81Uyj0N7lPclU1pUG.jpeg","isPro":false,"fullname":"Skanda Koppula","user":"skoppula","type":"user"},"name":"Skanda Koppula","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:47:12.071Z","hidden":false},{"_id":"668f4967f65238b10c6b12c4","user":{"_id":"5f881856ee5616341bc51e67","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f881856ee5616341bc51e67/9UCZCuhBTpJC9tGPyGmMb.jpeg","isPro":false,"fullname":"Fangyu Liu","user":"fl399","type":"user"},"name":"Fangyu Liu","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:47:30.850Z","hidden":false},{"_id":"668f4967f65238b10c6b12c5","name":"Adam Grycner","hidden":false},{"_id":"668f4967f65238b10c6b12c6","user":{"_id":"62d8f9887b8dc0ba17271415","avatarUrl":"/avatars/12ec78d34fd849bad44217b212f31e98.svg","isPro":false,"fullname":"Alexey Gritsenko","user":"AlexeyG","type":"user"},"name":"Alexey Gritsenko","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:47:44.594Z","hidden":false},{"_id":"668f4967f65238b10c6b12c7","user":{"_id":"64a2c7f263f69fb98d3bfdb4","avatarUrl":"/avatars/a362a236c0654b7605dcb7673e309335.svg","isPro":false,"fullname":"Neil Houlsby","user":"neilhoulsby","type":"user"},"name":"Neil Houlsby","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:47:51.045Z","hidden":false},{"_id":"668f4967f65238b10c6b12c8","name":"Manoj Kumar","hidden":false},{"_id":"668f4967f65238b10c6b12c9","user":{"_id":"648a9083abcf427a9a498679","avatarUrl":"/avatars/e32d413ce0a48d83f95e29c11a8a8ae8.svg","isPro":false,"fullname":"Keran ","user":"Keeera","type":"user"},"name":"Keran Rong","status":"claimed_verified","statusLastChangedAt":"2025-02-13T08:27:11.967Z","hidden":false},{"_id":"668f4967f65238b10c6b12ca","user":{"_id":"640f5502a92fedb0e8511d66","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/640f5502a92fedb0e8511d66/3CFOBG_gm4WlQpQXXaQlr.jpeg","isPro":false,"fullname":"Julian Eisenschlos","user":"eisenjulian","type":"user"},"name":"Julian Eisenschlos","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:48:23.777Z","hidden":false},{"_id":"668f4967f65238b10c6b12cb","name":"Rishabh Kabra","hidden":false},{"_id":"668f4967f65238b10c6b12cc","name":"Matthias Bauer","hidden":false},{"_id":"668f4967f65238b10c6b12cd","name":"Matko Bošnjak","hidden":false},{"_id":"668f4967f65238b10c6b12ce","name":"Xi Chen","hidden":false},{"_id":"668f4967f65238b10c6b12cf","user":{"_id":"649ac6e57c36fc2dc6e6b0f4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/649ac6e57c36fc2dc6e6b0f4/Scd3LiYW5Y2qunDDHnPWw.jpeg","isPro":false,"fullname":"Matthias Minderer","user":"mjlm","type":"user"},"name":"Matthias Minderer","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:48:54.125Z","hidden":false},{"_id":"668f4967f65238b10c6b12d0","name":"Paul Voigtlaender","hidden":false},{"_id":"668f4967f65238b10c6b12d1","user":{"_id":"666b0b1b0bc0ed84ea63b2e0","avatarUrl":"/avatars/0538f1c8a26d1afa1be90e3082c3791c.svg","isPro":false,"fullname":"Ioana Bica","user":"ioanabica","type":"user"},"name":"Ioana Bica","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:51:40.141Z","hidden":false},{"_id":"668f4967f65238b10c6b12d2","name":"Ivana Balazevic","hidden":false},{"_id":"668f4967f65238b10c6b12d3","user":{"_id":"64afea8efd620c8a7ad4ebd7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64afea8efd620c8a7ad4ebd7/O3e9nLirWFVZ_jMN4lFdH.jpeg","isPro":false,"fullname":"Joan Puigcerver","user":"joapuipe","type":"user"},"name":"Joan Puigcerver","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:51:19.650Z","hidden":false},{"_id":"668f4967f65238b10c6b12d4","name":"Pinelopi Papalampidi","hidden":false},{"_id":"668f4967f65238b10c6b12d5","user":{"_id":"64f30d8ceb5f2982081db604","avatarUrl":"/avatars/eedf65a104d099d8a60bbffe69bc2571.svg","isPro":false,"fullname":"Olivier Henaff","user":"olivierhenaff","type":"user"},"name":"Olivier Henaff","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:50:57.596Z","hidden":false},{"_id":"668f4967f65238b10c6b12d6","user":{"_id":"661bb651d9dc3639eb837e0c","avatarUrl":"/avatars/d038fb872833c66925f77db7d4baa559.svg","isPro":false,"fullname":"Xi Xiong","user":"alzmxx","type":"user"},"name":"Xi Xiong","status":"admin_assigned","statusLastChangedAt":"2024-07-11T16:23:51.810Z","hidden":false},{"_id":"668f4967f65238b10c6b12d7","name":"Radu Soricut","hidden":false},{"_id":"668f4967f65238b10c6b12d8","user":{"_id":"65d77c0e1e7686c460255fda","avatarUrl":"/avatars/1d26a7a7ffdc5ca9e67b97030f21b098.svg","isPro":false,"fullname":"Jeremiah Harmsen","user":"jharmsen","type":"user"},"name":"Jeremiah Harmsen","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:50:30.918Z","hidden":false},{"_id":"668f4967f65238b10c6b12d9","user":{"_id":"65dcd90082bddd501f68174b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/M2bc9PyKeFs1cCXjTfGGq.jpeg","isPro":false,"fullname":"Xiaohua Zhai","user":"xiaohuazhai","type":"user"},"name":"Xiaohua Zhai","status":"admin_assigned","statusLastChangedAt":"2024-07-11T08:50:23.887Z","hidden":false}],"publishedAt":"2024-07-10T14:57:46.000Z","submittedOnDailyAt":"2024-07-11T01:25:32.979Z","title":"PaliGemma: A versatile 3B VLM for transfer","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"PaliGemma is an open Vision-Language Model (VLM) that is based on the\nSigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to\nbe a versatile and broadly knowledgeable base model that is effective to\ntransfer. It achieves strong performance on a wide variety of open-world tasks.\nWe evaluate PaliGemma on almost 40 diverse tasks including standard VLM\nbenchmarks, but also more specialized tasks such as remote-sensing and\nsegmentation.","upvotes":72,"discussionId":"668f4968f65238b10c6b1317","ai_summary":"PaliGemma, a versatile Vision-Language Model based on SigLIP-So400m and Gemma-2B, demonstrates strong performance across numerous open-world tasks, including specialized areas like remote sensing and segmentation.","ai_keywords":["Vision-Language Model","SigLIP-So400m","Gemma-2B"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"668cd4bbe990292e5f6974d3","avatarUrl":"/avatars/d1747b2372e94500ecb5fb56809b482d.svg","isPro":false,"fullname":"Jinyeong Kim","user":"rubatoyeong","type":"user"},{"_id":"6281d941eeb15579946ca3ce","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6281d941eeb15579946ca3ce/0CdrBop_kjRkOqxUTYFbf.jpeg","isPro":false,"fullname":"Hui Sun","user":"CocoSun","type":"user"},{"_id":"6335150931a2be3938c99db6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6335150931a2be3938c99db6/g8pUPvi9ZI2ztW9fwee5_.png","isPro":false,"fullname":"Dokyoon","user":"leeloolee","type":"user"},{"_id":"60f1ab3afe0d78e01037eeb1","avatarUrl":"/avatars/f784fa423fd84fffb4683fa837ffc5a3.svg","isPro":false,"fullname":"Anas Awadalla","user":"anas-awadalla","type":"user"},{"_id":"62cd8442248f9e6bc20ad734","avatarUrl":"/avatars/8d1419f181462ed76e5336869f1d68e4.svg","isPro":false,"fullname":"Peter","user":"fourpartswater","type":"user"},{"_id":"6434b6619bd5a84b5dcfa4de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6434b6619bd5a84b5dcfa4de/h8Q6kPNjFNc03wmdboHzq.jpeg","isPro":false,"fullname":"Young-Jun Lee","user":"passing2961","type":"user"},{"_id":"642355b66e61cda1b3a12a87","avatarUrl":"/avatars/3bd950adeff89d06f40368935ef33944.svg","isPro":false,"fullname":"Ali","user":"andromeda26","type":"user"},{"_id":"616fb788e2ad27af26561b1a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1675485317568-616fb788e2ad27af26561b1a.jpeg","isPro":false,"fullname":"Xiao Xu","user":"LooperXX","type":"user"},{"_id":"6032802e1f993496bc14d9e3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6032802e1f993496bc14d9e3/w6hr-DEQot4VVkoyRIBiy.png","isPro":false,"fullname":"Omar Sanseviero","user":"osanseviero","type":"user"},{"_id":"635d618494e5b275ca73b844","avatarUrl":"/avatars/8cdaac6591a12b252612b99094e00959.svg","isPro":false,"fullname":"Levi","user":"Eladlev","type":"user"},{"_id":"642e686bbe01b88c9446db8b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/642e686bbe01b88c9446db8b/tb1DKe5xt50ykOeXiUuTE.jpeg","isPro":false,"fullname":"Lu Xudong","user":"lucky-lance","type":"user"},{"_id":"648c9605565e3a44f3c9bb7b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/648c9605565e3a44f3c9bb7b/W5chvk17Zol6-2QSWkFVR.jpeg","isPro":true,"fullname":"Orr Zohar","user":"orrzohar","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":1}">
PaliGemma, a versatile Vision-Language Model based on SigLIP-So400m and Gemma-2B, demonstrates strong performance across numerous open-world tasks, including specialized areas like remote sensing and segmentation.
AI-generated summary
PaliGemma is an open Vision-Language Model (VLM) that is based on the
SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to
be a versatile and broadly knowledgeable base model that is effective to
transfer. It achieves strong performance on a wide variety of open-world tasks.
We evaluate PaliGemma on almost 40 diverse tasks including standard VLM
benchmarks, but also more specialized tasks such as remote-sensing and
segmentation.