Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision
The paper introduces Tiny-Engram, a method for enhancing generative vision models by using trigger-indexed concept tables. This approach allows for better control over the retrieval of visual memories within frozen image and video generators. The results indicate that this method can improve modular visual personalization, particularly in image generation, while highlighting the need for further development in video generation.
- ▪Tiny-Engram provides an explicit lexical address and activation boundary for visual memories in generative models.
- ▪The method uses small sets of memory entries indexed by n-gram matches to modulate text-encoder hidden states.
- ▪Evaluation shows that while image generation benefits significantly, video generation still requires improvements for identity persistence.
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/2605.20309 |
| 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 | 74tIVmn_f-w3 |
| 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 > Computer Vision and Pattern Recognition arXiv:2605.20309 (cs) [Submitted on 19 May 2026] Title:Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision Authors:Runyuan Cai, Yiming Wang, Yu Lin, Xiaodong Zeng View a PDF of the paper titled Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision, by Runyuan Cai and Yiming Wang and Yu Lin and Xiaodong Zeng View PDF HTML (experimental) Abstract:Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide limited control over whether and when a concept should be retrieved.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
