ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection

arXiv:2610.05718 · cs.LG · Submitted 2026-10-05 · Read on arXiv

cs.LG

Submitted: 2026-10-05

Updated: 2026-10-05

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Domain Adaptation — 1× in this paper · explained in 5 episodes

Sources

• MobileCLIP2: Improving Multi-Modal Reinforced Training
• Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
• Delving into Out-of-Distribution Detection with Vision-Language Representations
• Mahalanobis++: Improving OOD Detection via Feature Normalization
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
• OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• Meta CLIP 2: A Worldwide Scaling Recipe
• In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks