Open-vocabulary object detection (OVD) is crucial for handling dynamic real-world driving scenarios. Inspired by YOLO-World, we propose OpenVocab-Auto, an open-vocabulary object detection framework with driving-aware multi-scale feature fusion for autonomous driving scenarios. Our system introduces three key innovations: (1) a context-adaptive prompt engine that significantly reduces computational overhead compared to global prompt strategies, (2) hierarchical vision-language alignment for improved small object detection, and (3) real-time optimization achieving 27 FPS on NVIDIA Jetson AGX Orin through TensorRT acceleration. On RTX 3080 (FP16 full model), the framework achieves 0.923 F1 for parking space detection and 0.847 F1 for zero-shot obstacle recognition. On Jetson Orin (TensorRT INT8 model), the corresponding scores are 0.811 and 0.333, respectively, under the same evaluation protocol.
This paper demonstrates the successful lab-to-fab transition of dynamic secondary-ion mass spectrometry (SIMS). In comparison to traditional lab SIMS, the in-line version is optimized for automated wafer and measurement sequence handling and high throughput measurements in small areas. Key advantages are fast turn-around time, reduced scrap, increased yield, and the measured wafer can continue processing in the manufacturing line. The benefits of in-line SIMS in the production environment are demonstrated for several use cases: matching and monitoring the long-term stability of epitaxy tools on monitor wafers, process optimization and monitoring of epitaxial Si and SiGe layers on blanket and patterned wafers with blanket metrology targets, measurement of implant and dopant profiles on blanket and patterned wafers, and characterization of the Ge and B diffusion in multi-layer stacks stimulated by high-temperature annealing. Additionally, the characterization of the source/drain epitaxy in a fully integrated nanosheet gate-all-around transistor architecture is demonstrated and discussed. The results are compared to off-line lab SIMS and alternative methods where available.
Power ISA™ Version 3.1 has introduced a new family of matrix math assist instructions, collectively known as the Matrix-Multiply Assist (MMA) facility. The instructions in this facility implement numerical linear algebra operations on small matrices and are meant to accelerate computation-intensive kernels. We advocate the use of compiler built-ins as the preferred way of leveraging these instructions. MMA built-ins are currently available in the GNU Compiler Collection and the LLVM-based IBM Open XL compilers. The built-ins are compatible across both compiler suites. We show that programming with these built-ins leads to efficient code that fully exploits the new facility.
This case report describes the detection, potential etiology, and progression of a ranibizumab injection (Susvimo) implant septum dislodgement in a patient with neovascular age-related macular degeneration.
Climate change is making extreme weather more extreme. Given the inherent uncertainty of long-term climate projections, there is growing need for rapid, plausible “what-if” climate scenarios to help users understand climate exposure and examine resilience and mitigation strategies. Since the 1980s, such “what-if” scenarios have been created using stochastic weather generators. However, it is very challenging for traditional weather generation algorithms to create realistic extreme climate scenarios because the weather data being modeled is highly imbalanced, contains spatiotemporal dependencies and has extreme weather events exacerbated by a changing climate. There are few works comparing and evaluating stochastic multisite (i.e., gridded) weather generators, and no existing work that compares promising deep learning approaches for weather generation with classical stochastic weather generators. We will present the culmination of a multi-year effort to perform a systematic evaluation of stochastic weather generators and deep generative models for multisite precipitation synthesis. Among other things, we show that variational auto-encoders (VAE) offer an encouraging pathway for efficient and controllable climate scenario synthesis – especially for extreme events. Our proposed VAE schema selects events with different characteristics in the normalized latent space (from rare to common) and generates high-quality scenarios using the trained decoder. Improvements are provided via latent space clustering and bringing histogram-awareness to the VAE loss. This research will serve as a guide for improving the design of deep learning architectures and algorithms for application in Earth science, including feature representation and uncertainty quantification of Earth system data and the characterization of so-called “grey swan” events.
