CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
The paper presents CP-MoE, a framework designed to tackle catastrophic forgetting in continual learning for large language and vision-language models. It introduces a transient expert mechanism that helps integrate task-specific updates while preserving important historical parameters. The proposed method demonstrates state-of-the-art performance on various benchmarks, effectively reducing forgetting and enhancing knowledge transfer across tasks.
- ▪CP-MoE addresses catastrophic forgetting in continual learning for large language models and vision-language models.
- ▪The framework utilizes a transient expert to capture task-specific updates and guide their integration into stable experts.
- ▪CP-MoE achieves state-of-the-art performance on the SuperNI benchmark and effectively reduces forgetting on the VQA v2 dataset.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20247 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | oFuV2PGQQ4e- |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.20247 (cs) [Submitted on 18 May 2026] Title:CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning Authors:Yang Liu, Toan Nguyen, Flora D. Salim View a PDF of the paper titled CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning, by Yang Liu and 2 other authors View PDF HTML (experimental) Abstract:Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
