In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves. We propose LatticeGen, a cooperative framework in which the server still handles most of the computation while the user controls the sampling operation. The key idea is that the true generated sequence is mixed with noise tokens by the user and hidden in a noised lattice. Considering potential attacks from a hypothetically malicious server and how the user can defend against it, we propose the repeated beam-search attack and the mixing noise scheme. In our experiments we apply LatticeGen to protect both prompt and generation. It is shown that while the noised lattice degrades generation quality, LatticeGen successfully protects the true generation to a remarkable degree under strong attacks (more than 50% of the semantic remains hidden as measured by BERTScore).
We study scalable machine learning models for full event reconstruction in high-energy electron-positron collisions based on a highly granular detector simulation. Particle-flow (PF) reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters or hits. We compare a graph neural network and kernel-based transformer and demonstrate that both avoid quadratic memory allocation and computational cost while achieving realistic PF reconstruction. We show that hyperparameter tuning on a supercomputer significantly improves the physics performance of the models. We also demonstrate that the resulting model is highly portable across hardware processors, supporting Nvidia, AMD, and Intel Habana cards. Finally, we demonstrate that the model can be trained on highly granular inputs consisting of tracks and calorimeter hits, resulting in a competitive physics performance with the baseline. Datasets and software to reproduce the studies are published following the findable, accessible, interoperable, and reusable (FAIR) principles.
Since radiologists have different training and clinical experience, they may provide various segmentation maps for a lung nodule. As a result, for a specific lung nodule, some regions have a higher chance of causing segmentation uncertainty, which brings difficulty for lung nodule segmentation with multiple annotations. To address this problem, this paper proposes an Uncertainty-Aware Segmentation Network (UAS-Net) based on multi-branch U-Net, which can learn the valuable visual features from the regions that may cause segmentation uncertainty and contribute to a better segmentation result. Meanwhile, this network can provide a Multi-Confidence Mask (MCM) simultaneously, pointing out regions with different segmentation uncertainty levels. We introduce a Feature-Aware Concatenation structure for different learning targets and let each branch have a specific learning preference. Moreover, a joint adversarial learning process is also adopted to help learn discriminative features of complex structures. Experimental results show that our method can predict the reasonable regions with higher uncertainty and improve lung nodule segmentation performance in LIDC-IDRI.