AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time Training

Xi Yang, Han Zhang, Zhijian Lin, Yibiao Hu, Hong Han

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 1 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 domain consistency constraint (Ldcc, VAE reconstruction+KL) (ablation)VDT · NewsCLIPpings (4 targets)F1 (%): B: 62.80 -> 72.26Improved
add Ldiva contrastive alignment loss (ablation)VDT · NewsCLIPpings (4 targets)F1 (%): B: 68.87 -> 72.26Improved
add test-time training (ablation)VDT · NewsCLIPpings (4 targets)F1 (%): B: 69.08 -> 72.26Improved
add confidence-variance filtering (ablation)VDT · NewsCLIPpings (4 targets)F1 (%): B: 68.13 -> 72.26Improved
VDT vs ConDA-TTT in U,W->BVDT · NewsCLIPpings (4 targets)F1 (%): 71.86 -> 72.26Improved
VDT vs ConDA-TTT in B,G->UVDT · NewsCLIPpings (4 targets)F1 (%): 81.03 -> 81.96Improved
use multi-source (BGW) instead of ConDA-TTT for target UVDT · NewsCLIPpings (4 targets)F1 (%): 80.42 -> 82.78Improved
VDT vs ConDA-TTT on single-source pairsVDT · NewsCLIPpings (4 targets)F1 (%): B->U: 77.16 -> 75.96; U->G: 75.07 -> 73.95; W->U: 82.27 -> 83.28Mixed

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