Δ-Mem: Efficient Online Memory for Large Language Models
The paper presents a new memory mechanism called δ-mem designed for large language models. This mechanism allows for efficient accumulation and reuse of historical information without the need for extensive context expansion. The results indicate that δ-mem significantly enhances performance on memory-intensive tasks while maintaining general capabilities.
- ▪δ-mem is a lightweight memory mechanism that augments a frozen full-attention backbone.
- ▪It compresses past information into a fixed-size state matrix updated by delta-rule learning.
- ▪The mechanism improves performance scores significantly on memory-heavy benchmarks.
2 outlets in our directory ran this story, first to last over 1 hour. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ 85. Embeddings and Vector Search: Memory for Language Models — DEV.to (Top)
Hacker News (Newest) files mainly under programming. We currently carry 5,306 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.org |
| Canonical URL | https://arxiv.org/abs/2605.12357 |
| Publication time | Sat, 16 May 2026 09:30:06 +0000 |
| Retrieval time | 2026-05-16T09:40:18.070Z |
| Last seen | 2026-05-16T09:40:18.070Z |
| 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 | 1Jc_S9o4eSMu · 2 stories |
| 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 > Artificial Intelligence arXiv:2605.12357 (cs) [Submitted on 12 May 2026] Title:$δ$-mem: Efficient Online Memory for Large Language Models Authors:Jingdi Lei, Di Zhang, Junxian Li, Weida Wang, Kaixuan Fan, Xiang Liu, Qihan Liu, Xiaoteng Ma, Baian Chen, Soujanya Poria View a PDF of the paper titled $\delta$-mem: Efficient Online Memory for Large Language Models, by Jingdi Lei and 9 other authors View PDF Abstract:Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
