The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Image, now support complex instruction following, realistic image synthesis, and controllable scene-text rendering. As these capabilities expan...
Fei-Fei Li, Run-Jie Wang, Xiao-Han Zhang et al.· 0 citations
A non-invasive model fingerprinting framework based on collapsed generation, a phenomenon where certain input conditions produce highly consistent images across multiple stochastic seeds, is presented, establishing collapsed generation as a reliable intrinsic evidence source for non-invasive diffusion model ownership v...
Yuanmin Huang, Chen Chen, Geng Hong et al.· 0 citations
This paper proposes an implicit video steganography framework that treats video hiding and recovery as a dual-stream generation process leveraging implicit neural representations, and introduces a dual-stream input encoding mechanism that decouples the input space into temporal and cryptographic encodings to ensure cov...
Yi-Fei Wang, Gaozhi Liu, Sheng Li et al.· Computer/law journal· 0 citations
OrchBench is established as an efficient and interpretable benchmark for comparing and diagnosing multi-agent orchestration plans, finding that preserving task-critical information is more important than simply increasing the number of agents, and the benefits of parallelism diminish as coordination failures accumulate...
