[
    {
        "id": "osp-21453",
        "type": "article-journal",
        "title": "Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning",
        "author": [
            {
                "family": "Zhao",
                "given": "Hongwei"
            },
            {
                "family": "Liu",
                "given": "Rui"
            },
            {
                "family": "Liu",
                "given": "Yansong"
            }
        ],
        "URL": "https://omanscience.com/en/articles/dynamic-lora-experts-and-prototype-ensemble-matching-for-class-incremental-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "DOI": "10.3390/app16126153",
        "abstract": "Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols."
    }
]