Viewing enriched Twitter post
🥳Excited to unveil the updated SEED (SEE & Draw), first released in Jul (quoted) and now updated: https://t.co/2vd7eKFuWm 🙌 SEED-LLaMA offers unified multimodal comprehension and generation, featuring multi-turn in-context emergent capabilities, akin to an AI aide (as below). https://t.co/6keEesD1cJ
{
"media": [
{
"id": "",
"type": "video",
"url": null,
"media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1710503301324922880/pu/img/vvtdP2txNz7rOtlW.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"nlp": {
"processed_at": "2025-08-06T12:41:56.180930",
"sentiment": "positive",
"topics": [
"LLMs",
"Machine Learning",
"Deep Learning",
"Neural Networks",
"AI Applications",
"NLP"
],
"ner": {
"entities": [
{
"entity": "SEED",
"type": "product"
},
{
"entity": "SEED-LLaMA",
"type": "product"
},
{
"entity": "Jul",
"type": "date"
},
{
"entity": "AI aide",
"type": "concept"
},
{
"entity": "multimodal comprehension",
"type": "feature"
}
]
}
},
"original_structure": "had_media_only"
}{
"user": {
"created_at": "2020-03-07T11:10:03.000Z",
"default_profile_image": false,
"description": "Researcher @ Tencent AI Lab and ARC Lab; # Vision and multimodal foundation models",
"fast_followers_count": 0,
"favourites_count": 302,
"followers_count": 663,
"friends_count": 362,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 8,
"location": "",
"media_count": 16,
"name": "Yixiao Ge",
"normal_followers_count": 663,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1236247703861915649/1583585094",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1345631186228396032/4Bb3luZ__normal.jpg",
"screen_name": "ge_yixiao",
"statuses_count": 72,
"translator_type": "none",
"url": "https://t.co/MjG0b77BZB",
"verified": false,
"withheld_in_countries": [],
"id_str": "1236247703861915649"
},
"id": "1710509538238157069",
"conversation_id": "1710509538238157069",
"full_text": "🥳Excited to unveil the updated SEED (SEE & Draw), first released in Jul (quoted) and now updated: https://t.co/2vd7eKFuWm 🙌\n\nSEED-LLaMA offers unified multimodal comprehension and generation, featuring multi-turn in-context emergent capabilities, akin to an AI aide (as below). https://t.co/6keEesD1cJ",
"reply_count": 1,
"retweet_count": 16,
"favorite_count": 63,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/2vd7eKFuWm",
"expanded_url": "https://arxiv.org/abs/2310.01218",
"display_url": "arxiv.org/abs/2310.01218"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1710503301324922880/pu/img/vvtdP2txNz7rOtlW.jpg",
"type": "video",
"video_url": "https://video.twimg.com/ext_tw_video/1710503301324922880/pu/vid/avc1/960x720/wKucOaECHHgK6I-H.mp4?tag=12"
}
],
"url": "https://twitter.com/ge_yixiao/status/1710509538238157069",
"created_at": "2023-10-07T04:17:08.000Z",
"#sort_index": "1715294783705665800",
"view_count": 54781,
"quote_count": 5,
"is_quote_tweet": true,
"is_retweet": false,
"is_pinned": false,
"is_truncated": false,
"startUrl": "https://twitter.com/ge_yixiao/status/1715294783705665791"
}