Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
A practitioner’s guide to continual multimodal pretraining
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ProtoAda uses format-aware prototypes for better task routing and geometry-aware consolidation to reduce interference in multimodal continual instruction tuning.
Introduces a representation-geometry-based taxonomy for continual learning in speech and audio, identifies mismatches with current CL assumptions in foundation models, and lists open challenges.
CRAM uses adaptive MoE with centroid routing and orthogonality constraints to enable parameter-efficient multimodal continual instruction tuning while mitigating forgetting.
A taxonomy survey of continual learning for vision-language models, grouping methods into multi-modal replay, cross-modal regularization, and parameter-efficient adaptation, with a review of benchmarks and metrics.
citing papers explorer
-
Black-Box Continual Learning for Vision-Language Models
Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
-
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.
-
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
Introduces a representation-geometry-based taxonomy for continual learning in speech and audio, identifies mismatches with current CL assumptions in foundation models, and lists open challenges.
-
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.
-
Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
A taxonomy survey of continual learning for vision-language models, grouping methods into multi-modal replay, cross-modal regularization, and parameter-efficient adaptation, with a review of benchmarks and metrics.
- DataComp-VLM: Improved Open Datasets for Vision-Language Models