Private Image Data joins a growing set of protections within the Moto Secure app, Motorola’s central hub for essential privacy and security tools powered by ThinkShield. From managing app permissions to securing sensitive files and monitoring device integrity, Moto Secure brings key Android and Motorola safeguards together in one place, making it easier for users to understand and manage their device’s security.
Abstract:Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior through external knowledge such as prompting, retrieval-augmented generation (RAG), or fine-tuning. We ask: do LLMs really need external context or parameters to adapt to different behaviors, or do they already have such knowledge embedded in their parameters? In this work, we show that LLMs already contain persona-specialized subnetworks in their parameter space. Using small calibration datasets, we identify distinct activation signatures associated with different personas. Guided by these statistics, we develop a masking strategy that isolates lightweight persona subnetworks. Building on the findings, we further discuss: how can we discover opposing subnetwork from the model that lead to binary-opposing personas, such as introvert-extrovert? To further enhance separation in binary opposition scenarios, we introduce a contrastive pruning strategy that identifies parameters responsible for the statistical divergence between opposing personas. Our method is entirely training-free and relies solely on the language model's existing parameter space. Across diverse evaluation settings, the resulting subnetworks exhibit significantly stronger persona alignment than baselines that require external knowledge while being more efficient. Our findings suggest that diverse human-like behaviors are not merely induced in LLMs, but are already embedded in their parameter space, pointing toward a new perspective on controllable and interpretable personalization in large language models.。业内人士推荐体育直播作为进阶阅读
。业内人士推荐搜狗输入法2026作为进阶阅读
It should be obvious, but don’t post personal stuff in a company or business-related chat, and refrain from posting work-related material in a group with friends or family.
Lex: FT’s flagship investment column，详情可参考爱思助手下载最新版本
All the winners at the 2026 Brit Awards