4 papers
One Framework for All: Cross-Modal Membership Inference for Generative Models
Dayong Ye, Tainqing Zhu, Kun Gao +6
Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inf…
Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
Zhenhao Xu, Wenhan Chang, Yichuan Chen +3
Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify mode…
Unveiling prethermalization and thermal processes through the simplest one-dimensional topological model
Guowen Yang, Jiale Wang, Yichuan Chen +5
Drawing on classical thermodynamic principles-such as the equipartition of energy and entropy maximization-extensive research has shown that the evolution of optical power in multi…
From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
Junhao Liu, Zhenhao Xu, Yuxin Fang +3
Recently, there have been notable advancements in large language models (LLMs), demonstrating their growing abilities in complex reasoning. However, existing research largely overl…