Viewing enriched Twitter post
Sakana AI research scientist Rujikorn (Tan) Charakorn recently presented Doc-to-LoRA at @MLCollective’s DLCT journal club, covering hypernetworks, cost amortization, and future directions. A very lively discussion followed. Many thanks to the organizers! https://t.co/kAKLdNvcLL https://t.co/NB6pJAsVyr
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2067624629926330530/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2067624629926330530/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-06-18T15:24:49.076984",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2067624629926330530",
"url": "https://x.com/SakanaAILabs/status/2067624629926330530",
"twitterUrl": "https://twitter.com/SakanaAILabs/status/2067624629926330530",
"text": "Sakana AI research scientist Rujikorn (Tan) Charakorn recently presented Doc-to-LoRA at @MLCollective’s DLCT journal club, covering hypernetworks, cost amortization, and future directions. A very lively discussion followed. Many thanks to the organizers!\n\nhttps://t.co/kAKLdNvcLL https://t.co/NB6pJAsVyr",
"source": "Twitter for iPhone",
"retweetCount": 5,
"replyCount": 0,
"likeCount": 24,
"quoteCount": 0,
"viewCount": 2371,
"createdAt": "Thu Jun 18 15:05:01 +0000 2026",
"lang": "en",
"bookmarkCount": 5,
"isReply": false,
"inReplyToId": null,
"conversationId": "2067624629926330530",
"displayTextRange": [
0,
279
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "SakanaAILabs",
"url": "https://x.com/SakanaAILabs",
"twitterUrl": "https://twitter.com/SakanaAILabs",
"id": "218811492",
"name": "Sakana AI",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1885939209388929024/dtnrOdGp_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/218811492/1686643464",
"description": "",
"location": "Tokyo, Japan",
"followers": 73226,
"following": 0,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Tue Nov 23 10:20:07 +0000 2010",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 406,
"statusesCount": 1141,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2036840833690071450"
],
"profile_bio": {
"description": "Sakana AI is an AI R&D company based in Tokyo.\n\nTry Sakana Marlin, Sakana Chat → https://t.co/1m2lSgnfB2",
"entities": {
"description": {
"urls": [
{
"display_url": "sakana.ai",
"expanded_url": "https://sakana.ai/",
"indices": [
81,
104
],
"url": "https://t.co/1m2lSgnfB2"
}
]
},
"url": {
"urls": [
{
"display_url": "sakana.ai/careers",
"expanded_url": "https://sakana.ai/careers",
"indices": [
0,
23
],
"url": "https://t.co/1q07mb3TzE"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/NB6pJAsVyr",
"expanded_url": "https://twitter.com/SakanaAILabs/status/2067624629926330530/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": [
{
"h": 57,
"w": 57,
"x": 7,
"y": 460
}
]
},
"orig": {
"faces": [
{
"h": 57,
"w": 57,
"x": 7,
"y": 460
}
]
}
},
"id_str": "2067624578260865025",
"indices": [
280,
303
],
"media_key": "3_2067624578260865025",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyxrZlkGxABCgACHLGtpWubgKIAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHLGtmWQbEAEKAAIcsa2la5uAogAA",
"media_key": "3_2067624578260865025"
}
},
"media_url_https": "https://pbs.twimg.com/media/HLGtmWQbEAEDFWo.jpg",
"original_info": {
"focus_rects": [
{
"h": 753,
"w": 1344,
"x": 0,
"y": 0
},
{
"h": 756,
"w": 756,
"x": 0,
"y": 0
},
{
"h": 756,
"w": 663,
"x": 0,
"y": 0
},
{
"h": 756,
"w": 378,
"x": 113,
"y": 0
},
{
"h": 756,
"w": 1344,
"x": 0,
"y": 0
}
],
"height": 756,
"width": 1344
},
"sizes": {
"large": {
"h": 756,
"w": 1344
}
},
"type": "photo",
"url": "https://t.co/NB6pJAsVyr"
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "youtube.com/watch?v=jb_0Xc…",
"expanded_url": "https://www.youtube.com/watch?v=jb_0XcBMJQU",
"indices": [
256,
279
],
"url": "https://t.co/kAKLdNvcLL"
}
],
"user_mentions": [
{
"id_str": "131244468",
"indices": [
88,
101
],
"name": "Mainline Collective",
"screen_name": "mlcollective"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "2027240298666209535",
"url": "https://x.com/SakanaAILabs/status/2027240298666209535",
"twitterUrl": "https://twitter.com/SakanaAILabs/status/2027240298666209535",
"text": "We’re excited to introduce Doc-to-LoRA and Text-to-LoRA, two related research exploring how to make LLM customization faster and more accessible.\n\nhttps://t.co/ApVzVsBuv1\n\nBy training a Hypernetwork to generate LoRA adapters on the fly, these methods allow models to instantly internalize new information or adapt to new tasks.\n\nBiological systems naturally rely on two key cognitive abilities: durable long-term memory to store facts, and rapid adaptation to handle new tasks given limited sensory cues. While modern LLMs are highly capable, they still lack this flexibility. Traditionally, adding long-term memory or adapting an LLM to a specific downstream task requires an expensive and time-consuming model update, such as fine-tuning or context distillation, or relies on memory-intensive long prompts.\n\nTo bypass these limitations, our work focuses on the concept of cost amortization. We pay the meta-training cost once to train a hypernetwork capable of producing tasks or document specific LoRAs on demand. This turns what used to be a heavy engineering pipeline into a single, inexpensive forward pass. Instead of performing per-task optimization, the hypernetwork meta-learns update rules to instantly modify an LLM given a new task description or a long document.\n\nIn our experiments, Text-to-LoRA successfully specializes models to unseen tasks using just a natural language description. Building on this, Doc-to-LoRA is able to internalize factual documents. On a needle-in-a-haystack task, Doc-to-LoRA achieves near-perfect accuracy on instances five times longer than the base model's context window. It can even generalize to transfer visual information from a vision-language model into a text-only LLM, allowing it to classify images purely through internalized weights.\n\nImportantly, both methods run with sub-second latency, enabling rapid experimentation while avoiding the overhead of traditional model updates. This approach is a step towards lowering the technical barriers of model customization, allowing end-users to specialize foundation models via simple text inputs. We have released our code and papers for the community to explore.\n\nDoc-to-LoRA\nPaper: https://t.co/87xEEpf0GN\nCode: https://t.co/zBfQi2L9LW\n\nText-to-LoRA\nPaper: https://t.co/emLRZ4Vdvo\nCode: https://t.co/b9mrdoWWRB",
"source": "Twitter for iPhone",
"retweetCount": 348,
"replyCount": 76,
"likeCount": 2158,
"quoteCount": 109,
"viewCount": 609406,
"createdAt": "Fri Feb 27 04:32:06 +0000 2026",
"lang": "en",
"bookmarkCount": 2062,
"isReply": false,
"inReplyToId": null,
"conversationId": "2027240298666209535",
"displayTextRange": [
0,
276
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "SakanaAILabs",
"url": "https://x.com/SakanaAILabs",
"twitterUrl": "https://twitter.com/SakanaAILabs",
"id": "218811492",
"name": "Sakana AI",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1885939209388929024/dtnrOdGp_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/218811492/1686643464",
"description": "",
"location": "Tokyo, Japan",
"followers": 73226,
"following": 0,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Tue Nov 23 10:20:07 +0000 2010",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 406,
"statusesCount": 1141,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2036840833690071450"
],
"profile_bio": {
"description": "Sakana AI is an AI R&D company based in Tokyo.\n\nTry Sakana Marlin, Sakana Chat → https://t.co/1m2lSgnfB2",
"entities": {
"description": {
"urls": [
{
"display_url": "sakana.ai",
"expanded_url": "https://sakana.ai/",
"indices": [
81,
104
],
"url": "https://t.co/1m2lSgnfB2"
}
]
},
"url": {
"urls": [
{
"display_url": "sakana.ai/careers",
"expanded_url": "https://sakana.ai/careers",
"indices": [
0,
23
],
"url": "https://t.co/1q07mb3TzE"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/gId3J6hgEr",
"expanded_url": "https://twitter.com/SakanaAILabs/status/2027240298666209535/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2027240151857176577",
"indices": [
277,
300
],
"media_key": "16_2027240151857176577",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAgoAARwiNC1l2yABCgACHCI0T5RbMP8AAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAACCgABHCI0LWXbIAEKAAIcIjRPlFsw/wAA",
"media_key": "16_2027240151857176577"
}
},
"media_url_https": "https://pbs.twimg.com/tweet_video_thumb/HCI0LWXbIAEKKAD.jpg",
"original_info": {
"focus_rects": [],
"height": 480,
"width": 1080
},
"sizes": {
"large": {
"h": 480,
"w": 1080
}
},
"type": "animated_gif",
"url": "https://t.co/gId3J6hgEr",
"video_info": {
"aspect_ratio": [
9,
4
],
"variants": [
{
"bitrate": 0,
"content_type": "video/mp4",
"url": "https://video.twimg.com/tweet_video/HCI0LWXbIAEKKAD.mp4"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "pub.sakana.ai/doc-to-lora/",
"expanded_url": "https://pub.sakana.ai/doc-to-lora/",
"indices": [
147,
170
],
"url": "https://t.co/ApVzVsBuv1"
},
{
"display_url": "arxiv.org/abs/2602.15902",
"expanded_url": "https://arxiv.org/abs/2602.15902",
"indices": [
2186,
2209
],
"url": "https://t.co/87xEEpf0GN"
},
{
"display_url": "github.com/SakanaAI/Doc-t…",
"expanded_url": "https://github.com/SakanaAI/Doc-to-LoRA",
"indices": [
2216,
2239
],
"url": "https://t.co/zBfQi2L9LW"
},
{
"display_url": "arxiv.org/abs/2506.06105",
"expanded_url": "https://arxiv.org/abs/2506.06105",
"indices": [
2261,
2284
],
"url": "https://t.co/emLRZ4Vdvo"
},
{
"display_url": "github.com/SakanaAI/Text-…",
"expanded_url": "https://github.com/SakanaAI/Text-to-LoRA",
"indices": [
2291,
2314
],
"url": "https://t.co/b9mrdoWWRB"
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}