AI Paper Atlas

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

Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models

Boyang Guo, Liang Li, Lin Peng, Yuhan Gao, Xichun Sheng, Chenggang Yan

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 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 L_TETF (ablation)IVLP baseline · Base-to-New (tau=0.25)harmonic mean: 70.35 -> 72.03Improved
add L_CC on top of L_TETF (ablation)CPT · Base-to-New (tau=0.25)harmonic mean: 72.03 -> 73.22Improved
add L_RS on top of L_TETF and L_CC (ablation)CPT · Base-to-New (tau=0.25)harmonic mean: 73.22 -> 73.58Improved
add L_RS on top of L_TETF (ablation)CPT · Base-to-New (tau=0.25)harmonic mean: 72.03 -> 72.42Improved
add all three losses (ablation)IVLP baseline · Domain generalization (tau=0.25)accuracy: 57.99 -> 60.16Improved
add all three losses (ablation)IVLP baseline · Base-to-New (tau=0.06)harmonic mean: 69.99 -> 72.47Improved
add L_CC on top of L_TETF (ablation)CPT · Base-to-New (tau=0.06)harmonic mean: 71.10 -> 71.85Improved
cosine K-means instead of Euclidean K-means (ablation)CPT · ImageNet base-to-new (tau=0.25)harmonic mean: 72.19 -> 72.62Improved
cosine K-means instead of spectral clustering (ablation)CPT · ImageNet base-to-new (tau=0.25)harmonic mean: 71.72 -> 72.62Improved
cosine K-means instead of K-medoids (ablation)CPT · ImageNet base-to-new (tau=0.25)harmonic mean: 71.86 -> 72.62Improved
cosine K-means instead of Euclidean K-means (ablation)CPT · ImageNet base-to-new (tau=0.06)seed std: 0.66 -> 0.52Improved
clusters of 16 prototypes (ablation)CPT · ImageNet base-to-newharmonic mean: 73.92Improved

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