Metraipolis › archive › dc_4bdaedafa108
Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation — arXiv:2610.22400
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22400
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:42:02.914Z
- SHA-256 of the archived text
896756904ad548b25a53d22496ced8273c544d0baf1c007bd67ca30d968ed1f4- Stable URL of this page
https://metraipolis.com/documento/dc_4bdaedafa108
How to cite
Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation — arXiv:2610.22400 — arXiv (en), https://arxiv.org/abs/2610.22400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bdaedafa108 (Metraipolis archive dc_4bdaedafa108, sha256 896756904ad548b25a53d22496ced8273c544d0baf1c007bd67ca30d968ed1f4)
BibTeX
@misc{dc4bdaedafa108,
title = {Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation — arXiv:2610.22400},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22400},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bdaedafa108; sha256 896756904ad548b25a53d22496ced8273c544d0baf1c007bd67ca30d968ed1f4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) prediction. However, their unidirectional constraint limits bidirectional information flow, hindering cross-modal interactions and the joint preservation of multi-source signals. Consequently, the learned static representations struggle to accommodate the distinct evidence requirements of diverse downstream scenarios. We address these limitations by unlocking the iterative denoising process of diffusion language models (dLLMs) as a multi-granularity reconstruction space. Based on this insight, we propose FINDERS (FactorIzatioN of Diffusion statEs for Routing across Scenarios), a router-equipped dLLM framework comprising four operations: denoise, factorize, route, and compress. Learnable meta-slots organize complementary denoising states into transferable cross-modal semantics and modality-specific behavioral factors. To provide grounded supervision, we construct BehaviorQA, a large-scale corpus containing explicit behavioral rationales. Guided by scenario queries, a lightweight router dynamically emphasizes relevant slot directions via an input-level residual pathway before cross-source fusion and final compression. Extensive experiments and online A/B tests across ten industrial scenarios demonstrate that FINDERS consistently outperforms state-of-the-art methods in both unified and scenario-adaptive settings. This work effectively pushes the boundaries of dLLMs beyond language generation, demonstrating their immense potential as powerful user representation learners. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.22400 — 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 2026-10-19T08:39:09.993Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).