AI Paper Atlas

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

TiME: Test-Time Mixture-of-Experts Routing via Asymmetric CO-Optimal Transport for Continual Test-Time Adaptation

Tianlun Liu, Zhiliang Tian, Zhen Huang, Tianle Liu, Xingzhi Zhou, Feng Liu, Dongsheng Li

ICML 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation

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 TiME routing (OR variant) on top of best baseline CTTA-TQwen1.5-MoE-A2.7B · TU stream avgaverage score: 0.4548 -> 0.4707Improved
add TiME (OR) over CTTA-T on DeepSeekDeepSeek-V2-Lite · TU stream avgaverage score: 0.4300 -> 0.4481Improved
use As-COOT instead of COOT (ablation)TiME · TU stream avg (Qwen)average score: 0.4553 -> 0.4707Improved
use As-COOT instead of Euclidean-distance allocation (ablation)TiME · TU stream avg (Qwen)average score: 0.4386 -> 0.4707Improved
use As-COOT instead of Hash Layer routing (ablation)TiME · TU stream avg (Qwen)average score: 0.4328 -> 0.4707Improved
add test-time online routing over original MoE routing (ablation)TiME · TU stream avg (Qwen)average score: 0.4354 -> 0.4707Improved
add semantic space alignment (SSA) (ablation)TiME · TU stream avg (Qwen)average score: 0.4517 -> 0.4707Improved
use Euclidean instead of cosine distance in SSA (ablation)TiME · TU stream avg (Qwen)average score: 0.4687 -> 0.4707No clear effect
use random restoration instead of L2 regularization (ablation)TiME · TU stream avg (Qwen)average score: 0.4641 -> 0.4707Improved
add random restoration of parameters (ablation)TiME · TU stream avg (Qwen)average score: 0.4534 -> 0.4707Improved
EOE vs OR compatibility construction in SSA (ablation)TiME · TU stream avg (Qwen)average score: 0.4661 vs 0.4707No clear effect
MoE base model instead of dense under TentTent · TU stream avgaverage score: 0.3543 -> 0.3887Improved

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