--- format: "aidr-story-markdown/v1" id: "0b0024271a7c2b5987bb318b30f07498aa6f526f34c941f4c96666004a752c83" canonical_url: "https://aidr.today/0b002427?lang=en" title: "Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-19T04:00:00.000Z" category: "Research" topics: ["llm"] source_urls: ["https://arxiv.org/abs/2610.22400"] summary: "FINDERS (FactorIzatioN of Diffusion statEs for Routing across Scenarios) is a router-equipped diffusion language model framework that uses the iterative denoising process as a multi-granularity reconstruction space for scenario-adaptive user representation. The framework comprises four operations—denoise, factorize, route, and compress—and uses learnable meta-slots to organize complementary denoising states into transferable cross-modal semantics and modality-specific behavioral factors. The authors also construct BehaviorQA, a large-scale corpus containing explicit behavioral rationales to provide grounded supervision." --- # Rethinking User Encoders: Routing Diffusion States for Scenario\-Adaptive User Representation > [Open the canonical story]() **Published:** 2026-10-19T04:00:00.000Z **Category:** Research **Topics:** llm ## Summary FINDERS \(FactorIzatioN of Diffusion statEs for Routing across Scenarios\) is a router\-equipped diffusion language model framework that uses the iterative denoising process as a multi\-granularity reconstruction space for scenario\-adaptive user representation\. The framework comprises four operations—denoise, factorize, route, and compress—and uses learnable meta\-slots to organize complementary denoising states into transferable cross\-modal semantics and modality\-specific behavioral factors\. The authors also construct BehaviorQA, a large\-scale corpus containing explicit behavioral rationales to provide grounded supervision\. ## Sources - [Story source]()