AI Paper Atlas

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

Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models

Mehran Tamjidi, Hamidreza Dastmalchi, Mohammadreza Alimoradijazi, Ali Cheraghian, Aijun An, Morteza Saberi

AAAI 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 2 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 cluster-based online prototyping to the source model (ablation)Uni3D-Large · ModelNet-40Ctop-1 accuracy: 59.15 -> 68.48Improved
add Prototype Reassignment (graph label smoothing) on top of online prototyping (ablation)Uni-Adapter · ModelNet-40Ctop-1 accuracy: 68.48 -> 69.70Improved
add Prototype Reassignment on top of online prototyping (ablation)Uni-Adapter · ShapeNet-Ctop-1 accuracy: 61.79 -> 62.41Improved
add Prototype Reassignment on top of online prototyping (ablation)Uni-Adapter · ScanObjectNN-Ctop-1 accuracy: 45.12 -> 46.33Improved
use cluster-based prototypes instead of confidence-based cache (ablation)Uni-Adapter · ShapeNet-Ctop-1 accuracyImproved
set label smoothing lambda_reg near 0 (negligible smoothing) (ablation)Uni-Adapter · ModelNet-40Ctop-1 accuracyHurt
too many or too few cluster centers (N) versus N=30 (ablation)Uni-Adapter · ModelNet-40Ctop-1 accuracyHurt
replace high-confidence dual cache (Point-Cache) with cluster cacheUni3D-Large · ShapeNet-Ctop-1 accuracy: 57.70 -> 62.41Improved
apply Uni-Adapter instead of Point-Cache on Objaverse-LVISULIP-2 · Objaverse-LVIS (clean)top-1 accuracy: 32.36 -> 31.83Hurt
add Uni-Adapter to source models vs Point-Cache on clean datasetsUni3D, OpenShape, ULIP-2 · clean small/large-scale datasetstop-1 accuracy: e.g. ModelNet OpenShape 84.04 -> 85.44Mixed

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