AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis

Pei Liu, Xiangxiang Zeng, Tengfei Ma, Yucheng Xing, Xuanbai Ren, Yiping Liu

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 1 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
merge cross-cancer task vectors with STEPH instead of cancer-specific trainingcancer-specific model · TCGA 13 cancers avgC-Index: 0.6609 -> 0.6949Improved
STEPH instead of representation-based transfer ROUPKTROUPKT · TCGA 13 cancers avgC-Index: 0.6812 -> 0.6949Improved
STEPH vs ROUPKT on COADROUPKT · TCGA-COADC-Index: 0.6708 -> 0.6698Hurt
add task vector mixup between target and source vectors (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6860 -> 0.6949Improved
use hypernetwork-driven lambda instead of trainable parameter (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6921 -> 0.6949Improved
use hypernetwork-driven w instead of trainable parameter w (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6490 -> 0.6949Improved
add sparsity (top-K) to aggregation (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6912 -> 0.6949Improved
add hypernetwork-driven w to existing merging methods (ablation)AdaMerging · TCGA 13 cancers avgC-Index: 0.5689 -> 0.6877Improved
add hypernetwork-driven w to TIES (ablation)TIES AM · TCGA 13 cancers avgC-Index: 0.6396 -> 0.6802Improved
use existing merging methods (Model Avg, AdaMerging, Surgery, Iso-C) for cross-cancer transfertarget model · TCGA 13 cancers avgC-Index: 0.6609 -> 0.5689..0.6396Hurt
add mixup coefficient penalty (beta=0.05 vs 0) (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6927 -> 0.6949No clear effect
add aggregation weight penalty (gamma>0 vs 0) (ablation)STEPH · TCGA 13 cancers avgC-Index: 0.6879 -> 0.6896No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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