🐦 Twitter Post Details

Viewing enriched Twitter post

@askalphaxiv

Yann LeCun 🤝 Saining Xie insane crossover of the 2 biggest visual representation researchers in the AI field “Beyond Language Modeling: An Exploration of Multimodal Pretraining” Right now, most multimodal models are basically a language model with a vision adapter bolted on, so they can describe images, but they don’t really think in images or video. This paper shows what happens when you do it the hard way: train one model from scratch on text, images, and video with a unified setup. They key idea is if you give the model a good visual internal format and it can use vision for both understanding and generating. Additionally, multimodal data can improve language instead of distracting it, and mixture-of-experts lets you scale vision’s huge data intake without bloating everything else. This paves the way towards changing the vision paradigm from “captioning add-on” model to native multimodal foundation model.

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2029644559391535314/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2029644559391535314/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-03-06T14:22:46.234135",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2029644559391535314",
  "url": "https://x.com/askalphaxiv/status/2029644559391535314",
  "twitterUrl": "https://twitter.com/askalphaxiv/status/2029644559391535314",
  "text": "Yann LeCun 🤝 Saining Xie\n\ninsane crossover of the 2 biggest visual representation researchers in the AI field\n\n“Beyond Language Modeling: An Exploration of Multimodal Pretraining”\n\nRight now, most multimodal models are basically a language model with a vision adapter bolted on, so they can describe images, but they don’t really think in images or video.\n\nThis paper shows what happens when you do it the hard way: train one model from scratch on text, images, and video with a unified setup.\n\nThey key idea is if you give the model a good visual internal format and it can use vision for both understanding and generating.\n\nAdditionally, multimodal data can improve language instead of distracting it, and mixture-of-experts lets you scale vision’s huge data intake without bloating everything else.\n\nThis paves the way towards changing the vision paradigm from “captioning add-on” model to native multimodal foundation model.",
  "source": "Twitter for iPhone",
  "retweetCount": 99,
  "replyCount": 11,
  "likeCount": 654,
  "quoteCount": 8,
  "viewCount": 48509,
  "createdAt": "Thu Mar 05 19:45:46 +0000 2026",
  "lang": "en",
  "bookmarkCount": 462,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2029644559391535314",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "askalphaxiv",
    "url": "https://x.com/askalphaxiv",
    "twitterUrl": "https://twitter.com/askalphaxiv",
    "id": "1722422481942884352",
    "name": "alphaXiv",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1866663567417806848/-Vj32Dq-_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1722422481942884352/1738960325",
    "description": "",
    "location": "",
    "followers": 34303,
    "following": 45,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Thu Nov 09 01:15:23 +0000 2023",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 3137,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 815,
    "statusesCount": 1729,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2029226538445820054"
    ],
    "profile_bio": {
      "description": "High fidelity research",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "alphaxiv.org",
              "expanded_url": "http://alphaxiv.org",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/7lQNcnzeZ7"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/itKoXYNyqf",
        "expanded_url": "https://twitter.com/askalphaxiv/status/2029644559391535314/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2029643423783809025",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2029643423783809025",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwqvfC/V3ABCgACHCq++SbWMNIAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHCq98L9XcAEKAAIcKr75JtYw0gAA",
            "media_key": "3_2029643423783809025"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HCq98L9XcAEwn7h.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 809,
              "w": 1444,
              "x": 0,
              "y": 0
            },
            {
              "h": 1444,
              "w": 1444,
              "x": 0,
              "y": 0
            },
            {
              "h": 1626,
              "w": 1426,
              "x": 0,
              "y": 0
            },
            {
              "h": 1626,
              "w": 813,
              "x": 0,
              "y": 0
            },
            {
              "h": 1626,
              "w": 1444,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1626,
          "width": 1444
        },
        "sizes": {
          "large": {
            "h": 1626,
            "w": 1444
          }
        },
        "type": "photo",
        "url": "https://t.co/itKoXYNyqf"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}