Tensor Cache: Eviction-conditioned Associative Memory for Transformers
The article introduces Tensor Cache, a novel two-level cache system designed for Transformers. It combines sliding-window softmax attention with a fixed-size outer-product fast-weight memory to enhance memory efficiency. This approach aims to improve the memory-quality frontier in long-context language modeling tasks.
- ▪Tensor Cache addresses the limitations of autoregressive Transformer KV caches that grow linearly with context length.
- ▪The system utilizes a first-level cache (L1) and a second-level cache (L2) to manage evicted tokens more effectively.
- ▪The proposed method enhances associative recall and memory capacity diagnostics in machine learning applications.
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/2605.22884 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| 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 | v-HhhUZJCiS- |
| 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:2605.22884 (cs) [Submitted on 21 May 2026] Title:Tensor Cache: Eviction-conditioned Associative Memory for Transformers Authors:Kabir Swain, Sijie Han, Daniel Karl I. Weidele, Mauro Martino, Antonio Torralba View a PDF of the paper titled Tensor Cache: Eviction-conditioned Associative Memory for Transformers, by Kabir Swain and 4 other authors View PDF HTML (experimental) Abstract:Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the window becomes inaccessible.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
