AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning

Dexia Chen, Qianjie Zhu, Weibing Li, Yue Yu, Tong Zhang, Ruixuan Wang

ICLR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 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 Manifold Alignment Regularization to cross-entropy (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 85.41 -> 86.44Improved
add Hierarchical Manifold Sculpting to cross-entropy (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 85.41 -> 86.20Improved
add HMS on top of MAR (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 86.44 -> 86.85Improved
add MAR on top of HMS (ablation)MPS-Tuning · ImageNet (16-shot)accuracy: 74.77 -> 75.60Improved
add global alignment alone to HMS baseline (ablation)MAR · 11-dataset average (1-shot)accuracy: 72.35 -> 73.42Improved
add local alignment alone to HMS baseline (ablation)MAR · 11-dataset average (16-shot)accuracy: 86.20 -> 86.67Improved
combine global and local alignment instead of local only (ablation)MAR · 11-dataset average (1-shot)accuracy: 72.82 -> 73.55Improved
use MAR instead of feature-level cosine consistency (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 86.07 -> 86.85Improved
use MAR instead of logit-level KL consistency (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 84.20 -> 86.85Improved
use feature-level L1 consistency instead of none (no regularizer) (ablation)HMS baseline · 11-dataset average (16-shot)accuracy: 86.20 -> 86.24No clear effect
apply HMS to earlier layers beyond the last two (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracyHurt
raise HMS weight lambda2 from 0.1 to 2 (ablation)MPS-Tuning · 11-dataset average (16-shot)accuracy: 86.85 -> 73.82Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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