This paper introduces Test-time Correction (TTC), an online 3D detection system designed to rectify test-time errors using various auxiliary feedback, aiming to enhance the safety of deployed autonomous driving systems. Unlike conventional offline 3D detectors that remain fixed during inference, TTC enables immediate online error correction without retraining, allowing autonomous vehicles to adapt to new scenarios and reduce deployment risks. To achieve this, we equip existing 3D detectors with an Online Adapter (OA) module-a prompt-driven query generator for real-time correction. At the core of OA module are visual prompts: image-based descriptions of objects of interest derived from auxiliary feedback such as mismatches with 2D detections, road descriptions, or user clicks. These visual prompts, collected from risky objects during inference, are maintained in a visual prompt buffer to enable continuous correction in future frames. By leveraging this mechanism, TTC consistently detects risky objects, achieving reliable, adaptive, and versatile driving autonomy. Extensive experiments show that TTC significantly improves instant error rectification over frozen 3D detectors, even under limited labels, zero-shot settings, and adverse conditions. We hope this work inspires future research on post-deployment online rectification systems for autonomous driving.

Graph matching aims to find node-to-node matching among multiple graphs, which is a fundamental yet challenging problem. To facilitate graph matching in scientific research and industrial applications, pygmtools is released, which is a Python graph matching toolkit that implements a comprehensive collection of two-graph matching and multi-graph matching solvers, covering both learning-free solvers as well as learning-based neural graph matching solvers. Our implementation supports numerical backends including Numpy, PyTorch, Jittor, Paddle, runs on Windows, MacOS and Linux, and is friendly to install and configure. Comprehensive documentations covering beginner's guide, API reference and examples are available online. pygmtools is open-sourced under Mulan PSL v2 license.

TCM treatment model is an effective tool to provide correct guidance and decision-making in clinical practice. Recently, traditional Chinese medicine (TCM) has become an increasingly concerned problem in the world, and it is still a hot research topic. However, most machine learning researches pursue the performance of the model, but ignore the trust mechanism of decision-making process. The interpretable TCM treatment model based on XGBoost integration is constructed in this paper, and the interpretability of the model is taken into account when the performance is good. AUC is selected as the main evaluation index of model performance, and other commonly used evaluation indexes are added in the comparative experiment: accuracy. The results show that the average performance of the proposed model is better than that of the traditional logistic regression algorithm. The interpretability of the model is considered in the selection of base classifier, feature selection and model integration. Finally, the whole model and the decision explanation to the specific samples are provided.