Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

MUSE dataset and benchmarks – Page 2 · SOTA2 Research

Research Datasets

MUSE

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Knowledge Retention

MUSE Retain set (Dr)

56KnowMem

9

Machine Unlearning

MUSE Books

99.56VerbMem

8

Machine Unlearning

MUSE Books

99.8VerbMem

8

Knowledge Unlearning

MUSE (forget set Df)

57.9VerbMem Df Pre

8

Relearning Attack

MUSE

43RAP

8

Multi-object referring segmentation

MUSE (test)

53.2gIoU

7

Bilingual Lexicon Induction

MUSE (test)

89.9P@1 (en-es →)

7

Cross-lingual Word Alignment

MUSE

81.84Alignment Score (IT-EN)

7

Knowledge Editing Transfer

MUSE-Books (test)

23.68KnowMem Score

6

Conversational Recommendation

MUSE Multimodal Fashion (test)

10.2R@1

5

Conversational Recommendation

MUSE (n=200)

4.16Recommendation Quality (Rec.Q)

3

Building energy consumption prediction

MUSE

3.05NMBE

2

Bilingual Lexicon Induction

MUSE zh-en (test)

96.6Precision

2

Page 2 of 2

Popular tasks

Machine Unlearning Conversational Recommendation Bilingual Lexicon Induction Knowledge Unlearning Reasoning Segmentation

Follow for updates

Join SOTA2 Contact