Metraipolis › archive › dc_f5fbf5d8cd9b

V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization — arXiv:2609.37198

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37198
License (as archived)
CC0-1.0
Archived
2026-10-07T16:23:37.291Z
SHA-256 of the archived text
73ded99d4257337371e849bfcd78803fdc697f3351dc30b5c7be4ed8151cde15
Stable URL of this page
https://metraipolis.com/documento/dc_f5fbf5d8cd9b

How to cite

V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization — arXiv:2609.37198 — arXiv (en), https://arxiv.org/abs/2609.37198 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5fbf5d8cd9b (Metraipolis archive dc_f5fbf5d8cd9b, sha256 73ded99d4257337371e849bfcd78803fdc697f3351dc30b5c7be4ed8151cde15)
BibTeX
@misc{dcf5fbf5d8cd9b,
  title = {V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization — arXiv:2609.37198},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37198},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5fbf5d8cd9b; sha256 73ded99d4257337371e849bfcd78803fdc697f3351dc30b5c7be4ed8151cde15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37198. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while preserving compositional control. Token-embedding methods are compact but often underfit identity, whereas adapter-based methods improve fidelity through persistent weight updates that can be costly to store and interfere when concepts are composed. We introduce V-Engram, a trigger-indexed external memory mechanism for Stable Diffusion 3.5. Each concept is assigned an explicit trigger that retrieves concept-specific memory, whose gated directions enter frozen text-encoder and MMDiT context states as relative residuals. Separating this memory from backbone adaptation enables prompt-selective and multi-concept access without merging model updates. Experiments show that V-Engram broadly matches DreamBooth-LoRA in overall subject fidelity while showing advantages in settings such as contextual subject preservation. Prompt-matched loading retrieves only matched entries, reducing most additional adaptation-state loading for a single-concept query. Qualitative results further demonstrate paired-trigger composition and same-class separation, while prompts without registered entries retain the frozen model's base behavior. Together, these results establish trigger-indexed memory as a modular interface for adding targeted visual evidence without rewriting the generator.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37198 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.600Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).