Research map / Continual learning / Domain and prompt-based
Learning To Prompt for Continual Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 an instance-wise prompt pool without rehearsal buffer | L2P · Split CIFAR-100 | Average Acc: 60.69 -> 83.83 | Helped |
| Use an instance-wise prompt pool without rehearsal buffer | L2P · 5-datasets | Average Acc: 50.93 -> 81.14 | Helped |
| Use an instance-wise prompt pool without rehearsal buffer | L2P · CORe50 | Test Acc: 75.45 -> 78.33 | Helped |
| Use an instance-wise prompt pool without rehearsal buffer | L2P · Gaussian scheduled CIFAR-100 | Test Acc: 63.04 -> 88.34 | Helped |
| Add a prompt pool rather than train a single shared prompt (ablation) | L2P · 5-datasets | Average Acc: 51.96 -> 81.14 | Helped |
| Add a prompt pool rather than train a single shared prompt (ablation) | L2P · 5-datasets | Forgetting: 26.60 -> 4.64 | Helped |
| Use learned key-value pairs instead of mean-of-prompts keys (ablation) | L2P · 5-datasets | Average Acc: 58.33 -> 81.14 | Helped |
| Use learned key-value pairs instead of mean-of-prompts keys (ablation) | L2P · 5-datasets | Forgetting: 20.45 -> 4.64 | Helped |
| Use diversified prompt selection (ablation) | L2P · 5-datasets | Average Acc: 62.26 -> 81.14 | Helped |
| Use diversified prompt selection (ablation) | L2P · 5-datasets | Forgetting: 17.84 -> 4.64 | Helped |
Closest papers by meaning
- Vector Quantization Prompting for Continual Learning (NeurIPS 2024 · similarity 0.91)
- Consistent Prompting for Rehearsal-Free Continual Learning (CVPR 2024 · similarity 0.91)
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.91)
- Evolving Parameterized Prompt Memory for Continual Learning (AAAI 2024 · similarity 0.91)
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning (NeurIPS 2025 · similarity 0.90)
- Mixture of Experts Meets Prompt-Based Continual Learning (NeurIPS 2024 · similarity 0.90)
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.