RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
Deep hashing network for unsupervised domain adaptation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
roles
dataset 2polarities
use dataset 2representative citing papers
Unimodal model representations converge to a relational structure captured by the Indra representation via V-enriched Yoneda embedding, which is unique and structure-preserving and improves cross-model and cross-modal robustness when instantiated with angular distance.
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
SAGE, an optimizer combining spectral polar-factor perturbation with gradient-agreement-scaled noise, reports 78.9% average on DomainBed.
citing papers explorer
-
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
-
The Indra Representation Hypothesis for Multimodal Alignment
Unimodal model representations converge to a relational structure captured by the Indra representation via V-enriched Yoneda embedding, which is unique and structure-preserving and improves cross-model and cross-modal robustness when instantiated with angular distance.
-
Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
-
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
SAGE, an optimizer combining spectral polar-factor perturbation with gradient-agreement-scaled noise, reports 78.9% average on DomainBed.