Viewing enriched Twitter post
World-Action Models (WAMs) have become the second dominant recipe for robot foundation models, next to classical VLAs. So where do they come from, and how do they compare vs VLAs? I wrote an small overview of the WAM landscape, with some personal takes: https://t.co/6S4gH9tWTt
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2066530578720022835/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2066530578720022835/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-06-15T18:04:40.296788",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2066530578720022835",
"url": "https://x.com/moritz_reuss/status/2066530578720022835",
"twitterUrl": "https://twitter.com/moritz_reuss/status/2066530578720022835",
"text": "World-Action Models (WAMs) have become the second dominant recipe for robot foundation models, next to classical VLAs.\n\nSo where do they come from, and how do they compare vs VLAs?\n\nI wrote an small overview of the WAM landscape, with some personal takes:\n\nhttps://t.co/6S4gH9tWTt",
"source": "Twitter for iPhone",
"retweetCount": 19,
"replyCount": 0,
"likeCount": 69,
"quoteCount": 6,
"viewCount": 7488,
"createdAt": "Mon Jun 15 14:37:38 +0000 2026",
"lang": "en",
"bookmarkCount": 70,
"isReply": false,
"inReplyToId": null,
"conversationId": "2066530578720022835",
"displayTextRange": [
0,
280
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "moritz_reuss",
"url": "https://x.com/moritz_reuss",
"twitterUrl": "https://twitter.com/moritz_reuss",
"id": "1714301210159661056",
"name": "Moritz Reuss",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1715675249373536256/0WHMLGP6_normal.jpg",
"coverPicture": "",
"description": "Robot learning @NVIDIARobotics (Seattle Robotics Lab). PhD @KITKarlsruhe. Opinions my own.",
"location": "",
"followers": 464,
"following": 382,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Tue Oct 17 15:24:17 +0000 2023",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "mbreuss.github.io",
"expanded_url": "https://mbreuss.github.io",
"indices": [
0,
23
],
"url": "https://t.co/1UQJzRMOds"
}
]
}
},
"fastFollowersCount": 0,
"favouritesCount": 513,
"hasCustomTimelines": false,
"isTranslator": false,
"mediaCount": 4,
"statusesCount": 42,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": {
"binding_values": [
{
"key": "photo_image_full_size_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=800x419",
"width": 800
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image",
"value": {
"image_value": {
"height": 150,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=280x150",
"width": 267
},
"type": "IMAGE"
}
},
{
"key": "description",
"value": {
"string_value": "Quick glossary for readers new to VLA/WAM terminology VLA Vision-Language-Action model: a robot policy that starts from a pretrained VLM backbone and adapts it to generate actions from visual…",
"type": "STRING"
}
},
{
"key": "domain",
"value": {
"string_value": "developer.nvidia.com",
"type": "STRING"
}
},
{
"key": "thumbnail_image_large",
"value": {
"image_value": {
"height": 320,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=800x320_1",
"width": 569
},
"type": "IMAGE"
}
},
{
"key": "summary_photo_image_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=386x202",
"width": 386
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_original",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=orig",
"width": 960
},
"type": "IMAGE"
}
},
{
"key": "photo_image_full_size_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=386x202",
"width": 386
},
"type": "IMAGE"
}
},
{
"key": "summary_photo_image_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=800x419",
"width": 800
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_small",
"value": {
"image_value": {
"height": 81,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=144x144",
"width": 144
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_x_large",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=png&name=2048x2048_2_exp",
"width": 960
},
"type": "IMAGE"
}
},
{
"key": "photo_image_full_size_original",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=orig",
"width": 960
},
"type": "IMAGE"
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "developer.nvidia.com",
"type": "STRING"
}
},
{
"key": "photo_image_full_size",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=600x314",
"width": 600
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 76.12,
"rgb": {
"blue": 242,
"green": 244,
"red": 244
}
},
{
"percentage": 6.29,
"rgb": {
"blue": 109,
"green": 119,
"red": 110
}
},
{
"percentage": 4.64,
"rgb": {
"blue": 36,
"green": 168,
"red": 107
}
},
{
"percentage": 3.8,
"rgb": {
"blue": 90,
"green": 148,
"red": 101
}
},
{
"percentage": 1.46,
"rgb": {
"blue": 225,
"green": 206,
"red": 190
}
}
]
},
"type": "IMAGE_COLOR"
}
},
{
"key": "title",
"value": {
"string_value": "Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models | NVIDIA Technical Blog",
"type": "STRING"
}
},
{
"key": "summary_photo_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 76.12,
"rgb": {
"blue": 242,
"green": 244,
"red": 244
}
},
{
"percentage": 6.29,
"rgb": {
"blue": 109,
"green": 119,
"red": 110
}
},
{
"percentage": 4.64,
"rgb": {
"blue": 36,
"green": 168,
"red": 107
}
},
{
"percentage": 3.8,
"rgb": {
"blue": 90,
"green": 148,
"red": 101
}
},
{
"percentage": 1.46,
"rgb": {
"blue": 225,
"green": 206,
"red": 190
}
}
]
},
"type": "IMAGE_COLOR"
}
},
{
"key": "summary_photo_image_x_large",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=png&name=2048x2048_2_exp",
"width": 960
},
"type": "IMAGE"
}
},
{
"key": "summary_photo_image",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=600x314",
"width": 600
},
"type": "IMAGE"
}
},
{
"key": "photo_image_full_size_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 76.12,
"rgb": {
"blue": 242,
"green": 244,
"red": 244
}
},
{
"percentage": 6.29,
"rgb": {
"blue": 109,
"green": 119,
"red": 110
}
},
{
"percentage": 4.64,
"rgb": {
"blue": 36,
"green": 168,
"red": 107
}
},
{
"percentage": 3.8,
"rgb": {
"blue": 90,
"green": 148,
"red": 101
}
},
{
"percentage": 1.46,
"rgb": {
"blue": 225,
"green": 206,
"red": 190
}
}
]
},
"type": "IMAGE_COLOR"
}
},
{
"key": "photo_image_full_size_x_large",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=png&name=2048x2048_2_exp",
"width": 960
},
"type": "IMAGE"
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/6S4gH9tWTt",
"type": "STRING"
}
},
{
"key": "summary_photo_image_original",
"value": {
"image_value": {
"height": 540,
"url": "https://pbs.twimg.com/card_img/2066529917592829953/USPQITMU?format=jpg&name=orig",
"width": 960
},
"type": "IMAGE"
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "Swift",
"version": "12"
}
}
},
"name": "summary_large_image",
"url": "https://t.co/6S4gH9tWTt",
"user_refs_results": []
},
"place": {},
"entities": {
"urls": [
{
"display_url": "developer.nvidia.com/blog/pretraine…",
"expanded_url": "https://developer.nvidia.com/blog/pretrained-to-imagine-fine-tuned-to-act-the-rise-of-world-action-models/",
"indices": [
257,
280
],
"url": "https://t.co/6S4gH9tWTt"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
}