RCL preserves evidence-reliance in continual multimodal learning to reduce hidden forgetting beyond standard accuracy metrics.
Less confidence, less forgetting: Learning with a humbler teacher in exemplar-free class- incremental learning.Neural Networks, 179:106513, 2024a
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
ProtoAda uses format-aware prototypes for better task routing and geometry-aware consolidation to reduce interference in multimodal continual instruction tuning.
CRAM uses adaptive MoE with centroid routing and orthogonality constraints to enable parameter-efficient multimodal continual instruction tuning while mitigating forgetting.
Prism is a plug-in infrastructure for scalable, reproducible multimodal continual instruction tuning research.
MAny addresses dual-forgetting in multimodal continual instruction tuning via CPM and LPM merging strategies, delivering up to 8.57% accuracy gains on UCIT benchmarks without additional training.
citing papers explorer
-
Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
RCL preserves evidence-reliance in continual multimodal learning to reduce hidden forgetting beyond standard accuracy metrics.
-
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning
ProtoAda uses format-aware prototypes for better task routing and geometry-aware consolidation to reduce interference in multimodal continual instruction tuning.
-
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
CRAM uses adaptive MoE with centroid routing and orthogonality constraints to enable parameter-efficient multimodal continual instruction tuning while mitigating forgetting.
-
Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning
Prism is a plug-in infrastructure for scalable, reproducible multimodal continual instruction tuning research.
-
MAny: Merge Anything for Multimodal Continual Instruction Tuning
MAny addresses dual-forgetting in multimodal continual instruction tuning via CPM and LPM merging strategies, delivering up to 8.57% accuracy gains on UCIT benchmarks without additional training.