Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the ground-truth representation, is critical because it sets the ultimate limit of any model, even with infinite data and computation. We study this problem in a completely nonparametric setting, without relying on interventions, parametric forms, or structural constraints. We first prove that the structure between time steps and tasks is identifiable in a fully unsupervised manner, even when sequences lack strict temporal dependence and may exhibit disconnections, and task assignments can follow arbitrarily complex and interleaving structures. We then prove that, within each time step, the task-relevant latent representation can be disentangled from the irrelevant part under a simple sparsity regularization, without any additional information or parametric constraints. Together, these results establish a hierarchical foundation: task structure is identifiable across time steps, and task-relevant latent representations are identifiable within each step. To our knowledge, each result provides a first general nonparametric identifiability guarantee, and together they mark a step toward provably moving from generalist to specialist models.</p>\n","updatedAt":"2026-05-14T17:53:03.079Z","author":{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","fullname":"Yujia Zheng","name":"yujiazheng","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8695876598358154},"editors":["yujiazheng"],"editorAvatarUrls":["/avatars/b3f5321366bbbb2fd91624289fbea958.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.12733","authors":[{"_id":"6a060bb1b1a8cbabc9f09661","name":"Yujia Zheng","hidden":false},{"_id":"6a060bb1b1a8cbabc9f09662","name":"Fan Feng","hidden":false},{"_id":"6a060bb1b1a8cbabc9f09663","name":"Yuke Li","hidden":false},{"_id":"6a060bb1b1a8cbabc9f09664","name":"Shaoan Xie","hidden":false},{"_id":"6a060bb1b1a8cbabc9f09665","name":"Kevin Murphy","hidden":false},{"_id":"6a060bb1b1a8cbabc9f09666","name":"Kun Zhang","hidden":false}],"publishedAt":"2026-05-12T00:00:00.000Z","submittedOnDailyAt":"2026-05-14T00:00:00.000Z","title":"From Generalist to Specialist Representation","submittedOnDailyBy":{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","isPro":false,"fullname":"Yujia Zheng","user":"yujiazheng","type":"user","name":"yujiazheng"},"summary":"Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the ground-truth representation, is critical because it sets the ultimate limit of any model, even with infinite data and computation. We study this problem in a completely nonparametric setting, without relying on interventions, parametric forms, or structural constraints. We first prove that the structure between time steps and tasks is identifiable in a fully unsupervised manner, even when sequences lack strict temporal dependence and may exhibit disconnections, and task assignments can follow arbitrarily complex and interleaving structures. We then prove that, within each time step, the task-relevant latent representation can be disentangled from the irrelevant part under a simple sparsity regularization, without any additional information or parametric constraints. Together, these results establish a hierarchical foundation: task structure is identifiable across time steps, and task-relevant latent representations are identifiable within each step. To our knowledge, each result provides a first general nonparametric identifiability guarantee, and together they mark a step toward provably moving from generalist to specialist models.","upvotes":1,"discussionId":"6a060bb1b1a8cbabc9f09667","ai_summary":"Nonparametric identifiability results establish foundational guarantees for extracting task-relevant representations from generalist models without parametric assumptions or interventions.","ai_keywords":["identifiability","generalist model","specialist representation","nonparametric setting","temporal dependence","sparsity regularization","latent representation","disentanglement"],"organization":{"_id":"691d9a1012cc4d473e1c862f","name":"CarnegieMellonU","fullname":"Carnegie Mellon University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/6I146aJvxxlRCEbYFFAeQ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6804a894ea0734d6b26f19c3","avatarUrl":"/avatars/b3f5321366bbbb2fd91624289fbea958.svg","isPro":false,"fullname":"Yujia Zheng","user":"yujiazheng","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"691d9a1012cc4d473e1c862f","name":"CarnegieMellonU","fullname":"Carnegie Mellon University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/6I146aJvxxlRCEbYFFAeQ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.12733.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.12733 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.12733 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.12733 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.