{"slug": "gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning", "title": "GAP-Prompt: Gated Adaptive Prompting for Efficient Continual Learning", "summary": "Researchers propose Gated Adaptive Prompting (GAP-Prompt), a novel method for continual learning that introduces instance-level adaptability to prompt-based approaches, achieving state-of-the-art performance on CIFAR-100, ImageNet-R, and CUB-200 benchmarks. On the fine-grained CUB-200 dataset, GAP-Prompt reaches 87.29% accuracy, approaching the joint training upper bound of 88.00% and outperforming existing methods by a significant margin.", "body_md": "arXiv:2608.23782v1 Announce Type: new\nAbstract: Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge. While prompt-based methods integrated with pre-trained models offer a compelling solution by freezing the backbone, they often rely on static, task-level prompting strategies that overlook fine-grained intra-task diversity. In this paper, we propose Gated Adaptive Prompting (GAP-Prompt), a novel method that introduces instance-level adaptability to the prompting process. GAP-Prompt consists of three synergistic modules: (1) instance-conditioned gating, which dynamically determines optimal prompt injection layers for each individual image; (2) dynamic knowledge fusion, which performs instance-aware aggregation of current and historical prompts, enabling knowledge integration across tasks; and (3) shared prompt distillation, which anchors foundational knowledge in early shared layers to mitigate forgetting. Extensive evaluations on CIFAR-100, ImageNet-R, and CUB-200 benchmarks demonstrate that GAP-Prompt consistently achieves state-of-the-art performance. Notably, on the fine-grained CUB-200 dataset, GAP-Prompt reaches 87.29% accuracy, approaching the joint training upper bound (88.00%) and outperforming existing methods by a significant margin.", "url": "https://wpnews.pro/news/gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning", "canonical_source": "https://arxiv.org/abs/2608.23782", "published_at": "2026-08-26 04:00:00+00:00", "updated_at": "2026-08-26 04:12:56.625096+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["GAP-Prompt", "CIFAR-100", "ImageNet-R", "CUB-200"], "alternates": {"html": "https://wpnews.pro/news/gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning", "markdown": "https://wpnews.pro/news/gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning.md", "text": "https://wpnews.pro/news/gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning.txt", "jsonld": "https://wpnews.pro/news/gap-prompt-gated-adaptive-prompting-for-efficient-continual-learning.jsonld"}}