Research map / Continual learning / Continual fine-tuning of LLMs
One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
Minh Le, Bao-Ngoc Dao, Huy Nguyen, Quyen Tran, Anh Nguyen, Nhat Ho
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a sparse MoE shared prompt (SMoPE) instead of single shared prompt OVOR | OVOR · ImageNet-R (10 tasks) | FAA: 75.25 -> 79.32 | Improved |
| use SMoPE instead of VQ-Prompt | VQ-Prompt · CUB-200 (10 tasks) | FAA: 86.72 -> 87.43 | Improved |
| use SMoPE instead of VQ-Prompt on DINO-1K | VQ-Prompt · ImageNet-R (DINO-1K) | FAA: 68.42 -> 68.61 | No clear effect |
| add sparse expert selection to a single shared prompt (ablation) | One Prompt (prefix tuning) · ImageNet-R | accuracy | Improved |
| add adaptive noise for balanced expert utilization (ablation) | SMoPE · ImageNet-R | accuracy | Improved |
| add prompt-attention score aggregation alone (ablation) | One Prompt (prefix tuning) · ImageNet-R | accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- OVOR — OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning (ICLR 2024) · better on 6 of 6 shared results
- DualPrompt — DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning (ECCV 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Mixture of Experts Meets Prompt-Based Continual Learning (NeurIPS 2024 · similarity 0.93)
- Training Consistent Mixture-of-Experts-Based Prompt Generator for Continual Learning (AAAI 2025 · similarity 0.91)
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.90)
- Consistent Prompting for Rehearsal-Free Continual Learning (CVPR 2024 · similarity 0.89)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (NeurIPS 2025 · similarity 0.89)
- Evolving Parameterized Prompt Memory for Continual Learning (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
