AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation

Lin Li, Ziqi Jiang, Gefan Ye, Zhenqi He, Jiahui Li, Jun Xiao, Kwang-Ting Cheng, Long Chen

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add centripetal hyperbolic alignment (CHA) to CLIP-LoRA (ablation)CLIP-LoRA · difficult group avg, 16-shottop-1 accuracy: 76.1 -> 77.7Improved
add path-decoupled objective to flow matching (ablation)HFM (CHA) · difficult group avg, 16-shottop-1 accuracy: 77.7 -> 79.2Improved
add diameter-based stopping at inference (ablation)HFM (CHA+PO) · difficult group avg, 16-shottop-1 accuracy: 79.2 -> 79.8Improved
add entailment loss to the contrastive loss in CHA (ablation)HFM CHA · difficult group avg, 16-shottop-1 accuracy: 72.0 -> 79.8Improved
add contrastive loss to the entailment loss in CHA (ablation)HFM CHA · difficult group avg, 16-shottop-1 accuracy: 79.0 -> 79.8Improved
add inter-class decoupling loss to step-wise consistency loss (ablation)HFM PO · difficult group avg, 16-shottop-1 accuracy: 79.4 -> 79.8Improved
use hyperbolic geometry instead of Euclidean with same objectives (FMA*) (ablation)flow matching adaptation · difficult group avg, 16-shottop-1 accuracy: 77.9 -> 79.8Improved
add HFM objectives to Euclidean FMA (ablation)FMA · difficult group avg, 16-shottop-1 accuracy: 77.7 -> 77.9No clear effect
step-wise consistency supervision instead of velocity supervision in Euclidean FMA (ablation)FMA · difficult group avg, 16-shottop-1 accuracy: 77.7 -> 77.8No clear effect
step-wise consistency supervision instead of velocity supervision in HFM (ablation)HFM · difficult group avg, 16-shottop-1 accuracy: 78.8 -> 79.8Improved
plug HFM into CLIP-AdapterCLIP-Adapter · difficult group avg, 16-shottop-1 accuracy: 63.6 -> 72.3Improved
plug HFM into CLIP-LoRA with ViT-L/14CLIP-LoRA · difficult group avg, 16-shot, ViT-L/14top-1 accuracy: 81.0 -> 83.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy