Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while overlooking implicit user intents (e.g.,"where should I click next?"when a user is navigating a website) and fail to continuously update their u...
Cheng-Zhi Liu, Yu-Xiang Lai, Yuzhe Yang et al.· 0 citations
TTME is introduced, a plug-and-play test-time adaptation method that continually updates the external memory by distilling the experience to guide subsequent discovery without updating model weights, and established as an effective and computationally efficient alternative to TTT in the evaluated discovery settings.
Yepeng Liu, Sheng-Mai Chen, Xuandong Zhao et al.· 0 citations
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which preferences still hold, which were revised, and which constraints apply now. Retaining that information is not the same as acting on it, and the two are usually optimized as if they were. Keeping the informa...
Jing-Xuan Wu, Yuzhe Yang, Yi-Qiao Huang et al.· 0 citations
Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide personalized assistance. This access creates a persistent privacy risk: the agent must decide whether a given sensitive information should be disclosed to a particular p...