arXiv Proposes NURESA: Enabling Zero-Shot Transfer of Persistent Memory Between AI Models
arXiv introduces NURESA (Neural Unit with Retentive Self-Adaptive Architecture), a novel n…
ZICQ curates daily AI news and deep dives on models, open-source infrastructure, and developer field reports.
Submit an articleCurrent filter: Tag: #人类反馈 Clear filters
arXiv introduces NURESA (Neural Unit with Retentive Self-Adaptive Architecture), a novel n…
Agentic· 2026-11-03
arXiv has recently released a new research paper titled AuroraWorld, which addresses the c…
LLMs & Foundation Models· 2026-11-03
arXiv has released a comprehensive survey on Text-to-SQL systems, focusing on the latest a…
LLMs & Foundation Models· 2026-11-03
arXiv has released a comprehensive survey on early stopping methods for large reasoning mo…
Agentic· 2026-11-03
arXiv introduces a novel posterior-sampling agent designed to address decision-making chal…
Research & Papers· 2026-11-03
arXiv has released a study on cross-prompt reuse of entity-replacement responses, investig…
Research & Papers· 2026-11-03
arXiv has published a study on community-based AI auditing, highlighting the algorithmic h…
LLMs & Foundation Models· 2026-11-03
arXiv introduces the Jacobian Lens (J-Lens) neural artifact to enhance depth pruning for l…
Research & Papers· 2026-11-03
arXiv introduces the Generalized Sparse Fuzzy Clustering (GSFC) framework, which addresses…
LLMs & Foundation Models· 2026-11-03
RandHan has released ResMem, a novel model that transforms retrieved knowledge into parame…
LLMs & Foundation Models· 2026-11-03
Hugging Face has released Circuit Oracle, an LLM-based tool designed to automate attributi…
Research & Papers· 2026-11-03
This research conducts a systematic audit of AI text humanizers, evaluating their ability …