@NielsRogge
Very cool work!! Modality Forcing gets SOTA on 4 out of 5 monocular depth estimation benchmarks. 🏆 Explore the paper and evals here: https://t.co/i9WcxlpIdY https://t.co/eKNlbOUqWu
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065784186921742731/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065784186921742731/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
},
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065784186921742731/media_1.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2065784186921742731/media_1.jpg",
"type": "photo",
"filename": "media_1.jpg"
}
],
"processed_at": "2026-06-13T22:33:43.626869",
"pipeline_version": "2.0"
}🔧 Raw API Response
{
"type": "tweet",
"id": "2065784186921742731",
"url": "https://x.com/NielsRogge/status/2065784186921742731",
"twitterUrl": "https://twitter.com/NielsRogge/status/2065784186921742731",
"text": "Very cool work!!\n\nModality Forcing gets SOTA on 4 out of 5 monocular depth estimation benchmarks. 🏆\n\nExplore the paper and evals here: https://t.co/i9WcxlpIdY https://t.co/eKNlbOUqWu",
"source": "Twitter for iPhone",
"retweetCount": 3,
"replyCount": 1,
"likeCount": 12,
"quoteCount": 0,
"viewCount": 2544,
"createdAt": "Sat Jun 13 13:11:45 +0000 2026",
"lang": "en",
"bookmarkCount": 9,
"isReply": false,
"inReplyToId": null,
"conversationId": "2065784186921742731",
"displayTextRange": [
0,
158
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "NielsRogge",
"url": "https://x.com/NielsRogge",
"twitterUrl": "https://twitter.com/NielsRogge",
"id": "133818617",
"name": "Niels Rogge",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1828883496066060288/n0OUAXhz_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/133818617/1636026056",
"description": "",
"location": "Belgium",
"followers": 20750,
"following": 727,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Fri Apr 16 18:18:57 +0000 2010",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1897,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 815,
"statusesCount": 3344,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1575416431793119232"
],
"profile_bio": {
"description": "ML Engineer @ml6team @huggingface. @KU_Leuven grad. General interest in machine & deep learning. Making AI more accessible for everyone!",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "",
"indices": [
12,
20
],
"name": "",
"screen_name": "ml6team"
},
{
"id_str": "",
"indices": [
21,
33
],
"name": "",
"screen_name": "huggingface"
},
{
"id_str": "",
"indices": [
35,
45
],
"name": "",
"screen_name": "KU_Leuven"
}
]
},
"url": {
"urls": [
{
"display_url": "nielsrogge.github.io",
"expanded_url": "http://nielsrogge.github.io",
"indices": [
0,
23
],
"url": "https://t.co/5ZROAxhmdm"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/eKNlbOUqWu",
"expanded_url": "https://twitter.com/NielsRogge/status/2065784186921742731/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2065784044349018112",
"indices": [
159,
182
],
"media_key": "3_2065784044349018112",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyrI6SyF9AACgACHKsjxeQW8YsAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHKsjpLIX0AAKAAIcqyPF5BbxiwAA",
"media_key": "3_2065784044349018112"
}
},
"media_url_https": "https://pbs.twimg.com/media/HKsjpLIX0AA_Ywz.jpg",
"original_info": {
"focus_rects": [
{
"h": 1222,
"w": 2182,
"x": 0,
"y": 0
},
{
"h": 1222,
"w": 1222,
"x": 226,
"y": 0
},
{
"h": 1222,
"w": 1072,
"x": 301,
"y": 0
},
{
"h": 1222,
"w": 611,
"x": 532,
"y": 0
},
{
"h": 1222,
"w": 2238,
"x": 0,
"y": 0
}
],
"height": 1222,
"width": 2238
},
"sizes": {
"large": {
"h": 1118,
"w": 2048
}
},
"type": "photo",
"url": "https://t.co/eKNlbOUqWu"
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "paperswithcode.co/paper/2606.136…",
"expanded_url": "https://paperswithcode.co/paper/2606.13676",
"indices": [
135,
158
],
"url": "https://t.co/i9WcxlpIdY"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "2065437358829531237",
"url": "https://x.com/BDuisterhof/status/2065437358829531237",
"twitterUrl": "https://twitter.com/BDuisterhof/status/2065437358829531237",
"text": "Introducing Modality Forcing, a recipe for post-training T2I models for SOTA RGB-Depth generation!\n\nText-to-image (T2I) models learn rich representations of the spatial world.\n\nHow do we build on this prior for high-quality depth generation?\n\nhttps://t.co/uJjGHNiDBu\n\n🧵 [1/6] https://t.co/JxyJjA64AW",
"source": "Twitter for iPhone",
"retweetCount": 27,
"replyCount": 4,
"likeCount": 134,
"quoteCount": 9,
"viewCount": 32896,
"createdAt": "Fri Jun 12 14:13:34 +0000 2026",
"lang": "en",
"bookmarkCount": 70,
"isReply": false,
"inReplyToId": null,
"conversationId": "2065437358829531237",
"displayTextRange": [
0,
275
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "BDuisterhof",
"url": "https://x.com/BDuisterhof",
"twitterUrl": "https://twitter.com/BDuisterhof",
"id": "1057351318841516032",
"name": "Bardienus Duisterhof",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2024161211726901248/K9BJuZkB_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1057351318841516032/1720110850",
"description": "",
"location": "USA",
"followers": 1049,
"following": 1009,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Oct 30 19:19:33 +0000 2018",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2226,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 34,
"statusesCount": 190,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2065437358829531237"
],
"profile_bio": {
"description": "MTS Research Intern at @theworldlabs || PhD Student @CMU_Robotics with @jeff_ichnowski || 4D Vision for Robot Manipulation 📷 | @bardienus.bsky.social | 🇳🇱",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "",
"indices": [
23,
36
],
"name": "",
"screen_name": "theworldlabs"
},
{
"id_str": "",
"indices": [
52,
65
],
"name": "",
"screen_name": "CMU_Robotics"
},
{
"id_str": "",
"indices": [
71,
86
],
"name": "",
"screen_name": "jeff_ichnowski"
},
{
"id_str": "",
"indices": [
128,
138
],
"name": "",
"screen_name": "bardienus"
}
]
},
"url": {
"urls": [
{
"display_url": "bart-ai.com",
"expanded_url": "http://bart-ai.com",
"indices": [
0,
23
],
"url": "https://t.co/3tKjqYDmv7"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": true
},
"display_url": "pic.twitter.com/JxyJjA64AW",
"expanded_url": "https://twitter.com/BDuisterhof/status/2065437358829531237/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2065436426020478976",
"indices": [
276,
299
],
"media_key": "13_2065436426020478976",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARyp53x/GmAAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHKnnfH8aYAAAAA==",
"media_key": "13_2065436426020478976"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2065436426020478976/img/5jxAY5zzuttB0qSW.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "video",
"url": "https://t.co/JxyJjA64AW",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 25800,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2065436426020478976/pl/ykpmkFotLxp7_DoR.m3u8?tag=27&v=79d"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065436426020478976/vid/avc1/480x270/iuSjYuatJSdlDl5u.mp4?tag=27"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065436426020478976/vid/avc1/640x360/hgUkThTdMNFHCXFs.mp4?tag=27"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065436426020478976/vid/avc1/1280x720/MSCCY2_1SXCusvVw.mp4?tag=27"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065436426020478976/vid/avc1/1920x1080/5G5IAbfoLW-mILG2.mp4?tag=27"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "modality-forcing.github.io",
"expanded_url": "http://modality-forcing.github.io",
"indices": [
243,
266
],
"url": "https://t.co/uJjGHNiDBu"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}