🐦 Twitter Post Details

Viewing enriched Twitter post

@ShenyuanGao

πŸ€– How can we enable zero-shot generalization to unseen scenarios for robot world models? Thrilled to share DreamDojo 🌎 β€” an interactive robot world model pretrained on 44K hours of human egocentric videos, the largest and most diverse dataset to date for robot world model learning. Our model not only excels in generalization, but also supports real-time interaction at 10 FPS after distillation. It enables several important applications, including live teleoperation, policy evaluation, and model-based planning at test time. πŸ”— Project: https://t.co/hJIEiGXnKz πŸ“° Paper: https://t.co/oa5xr8Y2GH πŸ€— Code & models & datasets: https://t.co/A8B4ii0Kah #WorldModels #Robotics #EmbodiedAI #RL #AI #NVIDIA Sharing more details in the thread 🧡

Media 2

πŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2024898256334114876/media_0.mp4?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2024898256334114876/media_0.mp4?",
      "type": "video",
      "filename": "media_0.mp4"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2024898256334114876/media_2.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2024898256334114876/media_2.jpg?",
      "type": "photo",
      "filename": "media_2.jpg"
    }
  ],
  "processed_at": "2026-03-01T19:14:36.207153",
  "pipeline_version": "2.0"
}

πŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2024898256334114876",
  "url": "https://x.com/ShenyuanGao/status/2024898256334114876",
  "twitterUrl": "https://twitter.com/ShenyuanGao/status/2024898256334114876",
  "text": "πŸ€– How can we enable zero-shot generalization to unseen scenarios for robot world models?\n\nThrilled to share DreamDojo 🌎 β€” an interactive robot world model pretrained on 44K hours of human egocentric videos, the largest and most diverse dataset to date for robot world model learning. Our model not only excels in generalization, but also supports real-time interaction at 10 FPS after distillation. It enables several important applications, including live teleoperation, policy evaluation, and model-based planning at test time.\nπŸ”— Project: https://t.co/hJIEiGXnKz\nπŸ“° Paper: https://t.co/oa5xr8Y2GH\nπŸ€— Code & models & datasets: https://t.co/A8B4ii0Kah\n\n#WorldModels #Robotics #EmbodiedAI #RL #AI #NVIDIA\n\nSharing more details in the thread 🧡",
  "source": "Twitter for iPhone",
  "retweetCount": 38,
  "replyCount": 15,
  "likeCount": 133,
  "quoteCount": 9,
  "viewCount": 53847,
  "createdAt": "Fri Feb 20 17:25:39 +0000 2026",
  "lang": "en",
  "bookmarkCount": 56,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2024898256334114876",
  "displayTextRange": [
    0,
    273
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "ShenyuanGao",
    "url": "https://x.com/ShenyuanGao",
    "twitterUrl": "https://twitter.com/ShenyuanGao",
    "id": "1854674102646456321",
    "name": "Shenyuan Gao",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/2023217771463815168/JxKAWYvk_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1854674102646456321/1771732346",
    "description": "",
    "location": "Local Minimum",
    "followers": 295,
    "following": 20,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Thu Nov 07 23:56:14 +0000 2024",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 113,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 10,
    "statusesCount": 68,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2024898256334114876"
    ],
    "profile_bio": {
      "description": "Research @NVIDIAAI | PhD @HKUST | World Models 🌎 | Robot Learning πŸ€–",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                9,
                18
              ],
              "name": "",
              "screen_name": "NVIDIAAI"
            },
            {
              "id_str": "0",
              "indices": [
                25,
                31
              ],
              "name": "",
              "screen_name": "HKUST"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "github.com/Little-Podi",
              "expanded_url": "https://github.com/Little-Podi",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/EbB9EF1PcP"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "additional_media_info": {
          "monetizable": false
        },
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/dCPm7R0xaX",
        "expanded_url": "https://twitter.com/ShenyuanGao/status/2024898256334114876/video/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "id_str": "2024897337404129280",
        "indices": [
          274,
          297
        ],
        "media_key": "13_2024897337404129280",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARwZ4WZmm4AAAAA=",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAAECgABHBnhZmabgAAAAA==",
            "media_key": "13_2024897337404129280"
          }
        },
        "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2024897337404129280/img/SA7h3riCVJSp8dhV.jpg",
        "original_info": {
          "focus_rects": [],
          "height": 1080,
          "width": 1920
        },
        "sizes": {
          "large": {
            "h": 1080,
            "w": 1920
          }
        },
        "type": "video",
        "url": "https://t.co/dCPm7R0xaX",
        "video_info": {
          "aspect_ratio": [
            16,
            9
          ],
          "duration_millis": 77451,
          "variants": [
            {
              "content_type": "application/x-mpegURL",
              "url": "https://video.twimg.com/amplify_video/2024897337404129280/pl/PINk653iL0KeS8og.m3u8?tag=21"
            },
            {
              "bitrate": 256000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2024897337404129280/vid/avc1/480x270/pnRfTs4JPxdWJ6wz.mp4?tag=21"
            },
            {
              "bitrate": 832000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2024897337404129280/vid/avc1/640x360/HiiALgg9_v3H3Jva.mp4?tag=21"
            },
            {
              "bitrate": 2176000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2024897337404129280/vid/avc1/1280x720/faelhNiyw9PT1ssR.mp4?tag=21"
            },
            {
              "bitrate": 10368000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2024897337404129280/vid/avc1/1920x1080/atuBitnBtuA-gMYh.mp4?tag=21"
            }
          ]
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [
      {
        "indices": [
          651,
          663
        ],
        "text": "WorldModels"
      },
      {
        "indices": [
          664,
          673
        ],
        "text": "Robotics"
      },
      {
        "indices": [
          674,
          685
        ],
        "text": "EmbodiedAI"
      },
      {
        "indices": [
          686,
          689
        ],
        "text": "RL"
      },
      {
        "indices": [
          690,
          693
        ],
        "text": "AI"
      },
      {
        "indices": [
          694,
          701
        ],
        "text": "NVIDIA"
      }
    ],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "dreamdojo-world.github.io",
        "expanded_url": "https://dreamdojo-world.github.io/",
        "indices": [
          541,
          564
        ],
        "url": "https://t.co/hJIEiGXnKz"
      },
      {
        "display_url": "arxiv.org/abs/2602.06949",
        "expanded_url": "https://arxiv.org/abs/2602.06949",
        "indices": [
          574,
          597
        ],
        "url": "https://t.co/oa5xr8Y2GH"
      },
      {
        "display_url": "github.com/NVIDIA/DreamDo…",
        "expanded_url": "https://github.com/NVIDIA/DreamDojo",
        "indices": [
          626,
          649
        ],
        "url": "https://t.co/A8B4ii0Kah"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}