AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Dataset Distillation by Influence Matching

Haoru Tan, Wang Wang, Sitong Wu, Xiuzhe Wu, Yang-Tian Sun, Chirui Chang, Shaofeng Zhang, Xiaojuan Qi

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 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 real-data initialization (ablation)Inf-Match · CIFAR-100 IPC=50accuracy (%): 52.2 -> 53.7Improved
add sampling schedule on top of real-data init (ablation)Inf-Match · CIFAR-100 IPC=50accuracy (%): 53.7 -> 55.0Improved
add learnable labels on top of real-data init (ablation)Inf-Match · CIFAR-100 IPC=50accuracy (%): 53.7 -> 54.6Improved
add learnable labels to real-data init plus sampling schedule (ablation)Inf-Match · CIFAR-100 IPC=50accuracy (%): 55.0 -> 57.4Improved
add sampling schedule to real-data init plus learnable labels (ablation)Inf-Match · CIFAR-100 IPC=50accuracy (%): 54.6 -> 57.4Improved
use outcome-influence matching instead of NCFM feature matchingInf-Match · CIFAR-100 IPC=50accuracy (%): 54.7 -> 57.4Improved
use influence matching instead of MTT trajectory matchingInf-Match · CIFAR-100 IPC=50accuracy (%): 47.7 -> 57.4Improved
use influence matching instead of DATMInf-Match · Flickr30K 500 pairs text-to-image retrievalrecall (%): 14.1 -> 14.6Improved
use influence matching instead of NCFMInf-Match · Tiny-ImageNet IPC=10accuracy (%): +4.7%Improved
use influence matching instead of NCFMInf-Match · CIFAR-100 IPC=50accuracy (%): 2.7%Improved

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