Smooth and collision-free trajectory planning is crucial to high speed and high precision machining, such as 3D laser cutting. However, it is difficult to further enhance the kinematic performance of the primary translational axes during the process. This paper presents a novel two-phase planning strategy, which optimizes the tool orientation and leverages a redundant standoff axis to significantly enhance the smoothness of the translational movements in redundant 3D laser cutting machines. In the first phase, collision-free configuration spaces (C-spaces) are constructed along the tool path, utilizing a graph-based search approach with Dijkstra's algorithm for tool orientation optimization. Subsequently, a secondary orientation curve, namely the M path, is planned in the second phase with a variable distance from the primary tool path curve, and the motion of the redundant standoff axis is handled via a deep reinforcement learning approach. The proposed methodology provides an advancement in conventional five-axis machines lacking of flexibility. Experimental validation confirms the potential of the approach to substantially improve machining accuracy and efficiency.

Chain of thought (CoT) prompting drives complex reasoning in large language models (LLMs), but remains scarcely explored for smaller Base Language Models (BLMs). We pioneer the Heuristic Chain of Thought (HCoT) approach for BLMs simply via "Let’s use knowledge" prompts. Further, we bridge the lack of guidance in HCoT by innovating SPIRE, a template providing specificity, purpose, information, role & capacity and expression to efficiently apply knowledge. Experiments show that combining HCoT with the SPIRE format significantly improves BLMs performance on question answering and translation tasks after minimal tuning. For example, on SQuADv1.1, our method increases the character F1 by 4.12% over zero-shot CoT using a 41.7M parameter BERT model.

Atlas building and image registration are important tasks for medical image analysis. Once one or multiple atlases from an image population have been constructed, commonly (1) images are warped into an atlas space to study intra-subject or inter-subject variations or (2) a possibly probabilistic atlas is warped into image space to assign anatomical labels. Atlas estimation and nonparametric transformations are computationally expensive as they usually require numerical optimization. Additionally, previous approaches for atlas building often define similarity measures between a fuzzy atlas and each individual image, which may cause alignment difficulties because a fuzzy atlas does not exhibit clear anatomical structures in contrast to the individual images. This work explores using a convolutional neural network (CNN) to jointly predict the atlas and a stationary velocity field (SVF) parameterization for diffeomorphic image registration with respect to the atlas. Our approach does not require affine pre-registrations and utilizes pairwise image alignment losses to increase registration accuracy. We evaluate our model on 3D knee magnetic resonance images (MRI) from the OAI-ZIB dataset. Our results show that the proposed framework achieves better performance than other state-of-the-art image registration algorithms, allows for end-to-end training, and for fast inference at test time.11Source code: https://github.com/uncbiag/Aladdin.

For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmentation success, while metrics related to label probabilities are not often explored. However, probability calibration approaches have been studied, which match probability outputs with experimentally observed errors. These approaches mainly focus on classification tasks, but not on semantic segmentation. Thus, we propose a learning-based calibration method that focuses on multi-label semantic segmentation. Specifically, we adopt a convolutional neural network to predict local temperature values for probability calibration. One advantage of our approach is that it does not change prediction accuracy, hence allowing for calibration as a postprocessing step. Experiments on the COCO, CamVid, and LPBA40 datasets demonstrate improved calibration performance for a range of different metrics. We also demonstrate the good performance of our method for multi-atlas brain segmentation from magnetic resonance images.