Changseon Yu, Hyeokjun Kweon · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31282 · open-access PDF
La personalización sin formación adapta un modelo de lenguaje de visión congelado (VLM) para reconocer conceptos definidos por el usuario a partir de sólo unos pocos ejemplares mediante la recuperación de entradas de conceptos en el momento de la inferencia. Mientras que los métodos recientes basados en el retriever enriquecen cada concepto con evidencia descriptiva, en gran medida tratan conceptos aislados, por lo que la información obtenida puede ser plausible pero no discriminatoria, especialmente cuando el conjunto de conceptos personalizados contiene categorías altamente confusas y finamente granuladas.
Machine translation (Meta M2M100); the English original follows.
Training-free personalization adapts a frozen vision-language model (VLM) to recognize user-defined concepts from only a few exemplars by retrieving concept entries at inference time. While recent retriever-based methods enrich each concept with descriptive evidence, they largely treat concepts in isolation, so the retrieved information can be plausible yet non-discriminative, especially when the personalized concept set contains highly confusable, fine-grained categories. We argue that personalization is inherently relational: correct recognition depends on the specific distinctions between a
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31282, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange