Viewing enriched Twitter post
PaLI-3 Vision Language Models: Smaller, Faster, Stronger abs: https://t.co/VATjcGkZXi Uses a 2B SigLIP vision encoder and 3B UL2 language model to obtain SOTA performance on visually-situated text understanding tasks. SigLIP observed to be a better encoder than classification-pretrained ViT. Model generalizes to video understanding tasks despite not being trained with videos.
{
"data": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/F8XLJh9awAA48_W.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"score": 0.89,
"scored_at": "2025-08-09T13:47:19.520807",
"import_source": "manual_curation_2023",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1712999591426285792/media_0.jpg?",
"filename": "media_0.jpg",
"original_url": "https://pbs.twimg.com/media/F8XLJh9awAA48_W.jpg"
}
],
"storage_migrated": true
}{
"user": {
"created_at": "2011-12-20T03:45:50.000Z",
"default_profile_image": false,
"description": "PhD at 19 |\nFounder and CEO at @MedARC_AI |\nResearch Director at @StabilityAI | \n@kaggle Notebooks GM |\nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/DwMkst4bnG",
"fast_followers_count": 0,
"favourites_count": 60004,
"followers_count": 45437,
"friends_count": 995,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 703,
"location": "",
"media_count": 1203,
"name": "Tanishq Mathew Abraham, PhD",
"normal_followers_count": 45437,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1675968078",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1553508977735962624/nnlSwBmu_normal.jpg",
"screen_name": "iScienceLuvr",
"statuses_count": 12087,
"translator_type": "none",
"url": "https://t.co/nNzCz2VVd1",
"verified": false,
"withheld_in_countries": [],
"id_str": "441465751"
},
"id": "1712999591426285792",
"conversation_id": "1712999591426285792",
"full_text": "PaLI-3 Vision Language Models: Smaller, Faster, Stronger\n\nabs: https://t.co/VATjcGkZXi\n\nUses a 2B SigLIP vision encoder and 3B UL2 language model to obtain SOTA performance on visually-situated text understanding tasks. SigLIP observed to be a better encoder than classification-pretrained ViT. Model generalizes to video understanding tasks despite not being trained with videos.",
"reply_count": 2,
"retweet_count": 15,
"favorite_count": 122,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/r25dK0yx15",
"expanded_url": "https://openreview.net/forum?id=JpyWPfzu0b",
"display_url": "openreview.net/forum?id=JpyWP…"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/media/F8XLJh9awAA48_W.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/iScienceLuvr/status/1712999591426285792",
"created_at": "2023-10-14T01:11:43.000Z",
"#sort_index": "1712999591426285792",
"view_count": 23231,
"quote_count": 2,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/iscienceluvr/status/1712999591426285792"
}