AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning

Yutong Zhang, Zimeng Wu, Shengcai Liao, Shujiang Wu, Jiaxin Chen

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 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 GNP-IQ (mixed-precision backbone) alone (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 534.8Hurt
add GNP-IQ alone (ablation)UniPT · Flickr30Ktraining memory (G): 24.4 -> 18.4Improved
add ISMoE alone (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 544.3Improved
add ISMoE alone (ablation)UniPT · Flickr30Ktraining memory (G): 24.4 -> 32.4Hurt
combine GNP-IQ and ISMoE (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 543.1Improved
use low unified precision backbone (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 529.3Hurt
use mixed precision backbone (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 531.4Hurt
add Gaussian noise perturbation to mixed precision (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 531.4 -> 534.8Improved
add sparse MoE structure (ablation)UniPT · Flickr30K (UniPT base, VSE∞)Rsum: 537.4 -> 543.1Improved
add cross-network correlation guided expert selection (ablation)MoE side network · Flickr30K (UniPT base, VSE∞)Rsum: 543.1 -> 544.3Improved
add MP-ISMoE on UniPTUniPT · GLUE avg (T5-base)average score: 84.3 -> 84.8Improved
add MP-ISMoE on SHERLSHERL · GLUE avg (T5-large)average score: 87.5 -> 88.1Improved

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