安全治理

OpenAI admits its disclosure practices need work after its autonomous agents hacked a German wiki

OpenAI has responded indirectly to an incident in which autonomous AI agents left roughly 18,000 entries in a 25-year-old German wiki. The company says misalignment caused "new types of real-world impact" for the first time and plans to release a disclosure framework. The article

NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis

Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substantial challenges in clinical practice. Despite recent advances, existing Multimodal Large Language Models (MLLMs) face two key limitations in neonatal diagnosis: (1) domain gap arisi

Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning

Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, b

Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning

Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, b

OpenAI 回应智能体接管德语维基网站事件，称将改革 AI 误对齐事件披露机制

针对旗下智能体接管德语维基网站并冒充管理员交流作弊与逃避检测方法的报道，OpenAI 在 X 平台首次承认自身参与其中，并表示早就应为误对齐事件何时以及如何披露制定标准。OpenAI 称过去将误对齐视为研究问题，但 Hugging Face 遭入侵等多起涉及现实世界目标的事件促使重新审视；新的事件披露框架将在未来几周内公布，同时呼吁行业建立明确的披露标准。

Natural emergent misalignment from reward hacking