Submitted to NeurIPS</p>\n","updatedAt":"2026-05-14T22:48:05.301Z","author":{"_id":"67735df3a4a6e0ad0625ed20","avatarUrl":"/avatars/dddedc3d852e6226345873b3ab7706e4.svg","fullname":"Salim Khazem","name":"salimkh97","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7896835207939148},"editors":["salimkh97"],"editorAvatarUrls":["/avatars/dddedc3d852e6226345873b3ab7706e4.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.08557","authors":[{"_id":"6a0650f8b1a8cbabc9f0973b","name":"Salim Khazem","hidden":false},{"_id":"6a0650f8b1a8cbabc9f0973c","name":"Ibrahim Mohamed Serouis","hidden":false},{"_id":"6a0650f8b1a8cbabc9f0973d","name":"Zakaria Ezzahed","hidden":false}],"publishedAt":"2026-05-08T00:00:00.000Z","submittedOnDailyAt":"2026-05-14T00:00:00.000Z","title":"MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching","submittedOnDailyBy":{"_id":"67735df3a4a6e0ad0625ed20","avatarUrl":"/avatars/dddedc3d852e6226345873b3ab7706e4.svg","isPro":false,"fullname":"Salim Khazem","user":"salimkh97","type":"user","name":"salimkh97"},"summary":"Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete Euclidean perturbation of frozen representations, without explicitly modeling the geometry of the task-induced feature displacement. We propose MC-RFM, a mixed-curvature Riemannian flow-matching framework for few-shot adaptation of frozen visual backbones. The key idea is to represent adapted features on a product manifold combining a hyperbolic factor, which captures hierarchy-sensitive semantic structure, and a Euclidean factor, which preserves locally discriminative visual variation. Adaptation is formulated as a task-conditioned continuous transport from frozen features to support-set prototypes, trained with a flow-matching objective and coupled to a hybrid prototype-linear classifier. The method is lightweight, backbone-agnostic, and operates entirely on cached frozen features. Across seven visual recognition benchmarks, five frozen backbones, and 1/4/16-shot regimes, MC-RFM is the best-performing method in a majority of evaluated settings, with the strongest gains on Transformer backbones and fine-grained datasets. Ablations show that the mixed-curvature head, task conditioning, adaptive branch gating, prototype shrinkage, and discriminative supervision each contribute to performance. These results suggest that few-shot adaptation benefits not only from deciding which parameters to update, but also from modeling how representations should move through a geometry matched to the structure of the downstream task.","upvotes":2,"discussionId":"6a0650f9b1a8cbabc9f0973e","githubRepo":"https://github.com/salimkhazem/MC-RFM","githubRepoAddedBy":"user","ai_summary":"A novel Riemannian flow-matching framework for few-shot adaptation that models feature displacement on a mixed-curvature manifold combining hyperbolic and Euclidean spaces, outperforming existing methods across multiple benchmarks.","ai_keywords":["parameter-efficient adaptation","vision models","Riemannian flow-matching","mixed-curvature manifold","hyperbolic factor","Euclidean factor","task-conditioned transport","flow-matching objective","hybrid prototype-linear classifier","few-shot adaptation","frozen visual backbones","product manifold","feature displacement","downstream task structure"],"githubStars":4,"organization":{"_id":"640cc93fd9fcfbf4a569ab47","name":"Talan","fullname":"Talan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/640cc8bec63516d41ed008c9/u3XPnnrj0EG1dUKYNwVZu.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"67735df3a4a6e0ad0625ed20","avatarUrl":"/avatars/dddedc3d852e6226345873b3ab7706e4.svg","isPro":false,"fullname":"Salim Khazem","user":"salimkh97","type":"user"},{"_id":"69f20a4bd3ddb0e7ef945eba","avatarUrl":"/avatars/ee55cfdc4f5575bc0153c4f30df55201.svg","isPro":false,"fullname":"Berahli","user":"amineberahli996","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"640cc93fd9fcfbf4a569ab47","name":"Talan","fullname":"Talan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/640cc8bec63516d41ed008c9/u3XPnnrj0EG1dUKYNwVZu.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.08557.md"}">
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
Abstract
A novel Riemannian flow-matching framework for few-shot adaptation that models feature displacement on a mixed-curvature manifold combining hyperbolic and Euclidean spaces, outperforming existing methods across multiple benchmarks.
AI-generated summary
Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete Euclidean perturbation of frozen representations, without explicitly modeling the geometry of the task-induced feature displacement. We propose MC-RFM, a mixed-curvature Riemannian flow-matching framework for few-shot adaptation of frozen visual backbones. The key idea is to represent adapted features on a product manifold combining a hyperbolic factor, which captures hierarchy-sensitive semantic structure, and a Euclidean factor, which preserves locally discriminative visual variation. Adaptation is formulated as a task-conditioned continuous transport from frozen features to support-set prototypes, trained with a flow-matching objective and coupled to a hybrid prototype-linear classifier. The method is lightweight, backbone-agnostic, and operates entirely on cached frozen features. Across seven visual recognition benchmarks, five frozen backbones, and 1/4/16-shot regimes, MC-RFM is the best-performing method in a majority of evaluated settings, with the strongest gains on Transformer backbones and fine-grained datasets. Ablations show that the mixed-curvature head, task conditioning, adaptive branch gating, prototype shrinkage, and discriminative supervision each contribute to performance. These results suggest that few-shot adaptation benefits not only from deciding which parameters to update, but also from modeling how representations should move through a geometry matched to the structure of the downstream task.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.08557 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.08557 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.08557 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.