AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation

Yongbo He, Zirun Guo, Tao Jin

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation · 3 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 stable adapter (ablation)DASP · Kinetics50-C (avg of Video-C, Audio-C, Interleaved-C)accuracy (%): 67.4 -> 68.4Improved
add plastic adapter (ablation)DASP · Kinetics50-C (avg of Video-C, Audio-C, Interleaved-C)accuracy (%): 66.0 -> 68.4Improved
add asymmetric adaptation (ablation)DASP · Kinetics50-C (avg of Video-C, Audio-C, Interleaved-C)accuracy (%): 62.5 -> 68.4Improved
use asymmetric adaptation as designed instead of opposite configuration (ablation)DASP · Kinetics50-C (avg of Video-C, Audio-C, Interleaved-C)accuracy (%): 61.9 -> 68.4Improved
add asymmetric adaptation (ablation)DASP · Kinetics50-C Video-Caccuracy (%): 54.3 -> 65.3Improved
add stable adapter (ablation)DASP · Kinetics50-C Interleaved-Caccuracy (%): 65.2 -> 67.3Improved
add stable adapter (ablation)DASP · Kinetics50-C Audio-Caccuracy (%): 72.3 -> 72.5No clear effect
use DASP over TSA under audio corruptionTSA · VGGSound-C audio (episodic)accuracy (%): 34.7 -> 39.7Improved
use DASP over TSA under interleaved corruptionTSA · Kinetics50-C interleaved (continual)accuracy (%): 63.9 -> 67.3Improved
use DASP instead of TSA on VGGSound-C interleaved continualTSA · VGGSound-C interleaved (continual)accuracy (%): 12.8 -> 52.5Improved
use DASP instead of Tent in continual video adaptationTent · Kinetics50-C video (continual)accuracy (%): 41.8 -> 65.3Improved
use DASP over TSA on VGGSound-C video corruptionTSA · VGGSound-C video (episodic)accuracy (%): 56.6 -> 57.5Improved

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