This paper presents RosettaStone 2.0, an open benchmark translation and evaluation framework built on OpenROAD-Research [1]. RosettaStone 2.0 provides complete RTL-to-GDS reference flows for both conventional 2D designs and Pin-3D-style face-to-face (F2F) hybrid-bonded 3D designs, enabling rigorous apples-to-apples comparison across planar and three-dimensional implementation settings. The framework is integrated within OpenROAD-flowscripts (ORFS)-Research [2]; it incorporates continuous integration (CI)-based regression testing and provides a standardized evaluation pipeline based on the METRICS2.1 convention, with structured logs and reports generated by ORFS-Research. To support transparent and reproducible research, RosettaStone 2.0 further provides a community-facing leaderboard, which is governed by verified pull requests and enforced through Developer Certificate of Origin (DCO) compliance.

This study investigates the application of semantic text similarity embedding models to address data interoperability challenges in the construction and civil engineering sectors. Research focuses on improving embedding models to produce domain-specific embeddings that precisely capture the complex terminology and relationships among various building systems, including Building Information Modeling, Building Energy Modeling, and Building Management Systems. In this study, we explored the use of embedding models to enhance semantic text similarity applications within the construction industry. The aim is to augment general-purpose language models by training them on a comprehensive construction and civil engineering data corpus to promote enhanced data integration and interoperability among diverse sources. Our methodology includes a comprehensive data collection and preprocessing pipeline, followed by a multi-stage fine-tuning approach that employs continuous pre-training, task-specific fine-tuning, and parameter-efficient adaptation algorithms. We assess the effectiveness of our models through intrinsic evaluations, including semantic similarity measures and domain-specific benchmarks. The test results demonstrate that our domain-adapted models, especially the Weight-Decomposed Low-Rank Adaptation method, substantially surpass the fundamental language models in domain-specific tasks, including understanding technical terms and data alignment across domains. The results of the models show significant performance enhancements with minimal resource investment, making them appropriate for practical use. Our research demonstrates that domain-specific embedding models can substantially improve data integration and enable more advanced, data-driven applications in the building industry.

While the recent advancements highlight the significant potential of the remote sensing foundation model in addressing Earth observation tasks, they require fine-tuning with task-specific data to transfer to various applications. Fine-tuning for each task greatly limits the generalizability of foundation models. The process directs the models toward the task-relevant information while less focus on the universal feature extraction for multiple tasks, which is considered the primary advantage of foundation models. Moreover, it also overlooks the complementary relationships among tasks, and significantly increases the computational complexity. However, simply training a model with multiple tasks also struggles to find effective representations of features. RSI interpretation tasks exhibit substantial finegrained differences, with each task potentially favoring features at different scales. Additionally, using the same features for all tasks can cause mutual interference, and the lack of multi-task datasets in remote sensing society hampers the generalization and sharing of visual features across tasks. To address these issues, we propose a multi-task fine-tuning framework,UniRS. To facilitate cross-scale feature interactions, we introduce the Cross-scale Generic Feature Interaction (CGFI) mechanism, which integrates multi-scale features and uses Generic Feature Query (GFQ) to achieve more generalized representations. Additionally, we propose the Task-specific Low-rank Mixture of Experts (TLMoE) Decomposition. General features are fed into multiple low-rank experts, each capable of capturing different patterns of the features. By dynamically combining the outputs of these experts, features for each sample and each task are encoded dynamically. Furthermore, we have expanded the existing datasets and developed MOTA, a new dataset annotated for three tasks: semantic segmentation, rotated object detection, and multi-label scene classification. Extensive experiments demonstrate the effectiveness of the well-designedUniRS. The code and dataset will be released at https://github.com/Duckyee728/UniRS.

While image semantic segmentation is a fundamental and well-studied task in remote sensing (RS) society, it usually depends on large amounts of pixel-level annotations. RS image semi-supervised semantic segmentation (RSIS4) tries to improve performance by exploring the unlabeled data, thus significantly reducing the label costs. The core idea of RSIS4 is to transfer the prior information from the labeled to unlabeled pixels, which is commonly achieved by considering the confident part of the softmax prediction as pseudolabels for further supervised learning. However, such pixel-level instruction could inevitably involve uncertainty (e.g., noise and error) due to the extremely limited annotated data at the initialization. To address this issue, in this letter, we employ the prototypes, which contain inbuilt resistance to potentially inaccurate pixels, to bring substantial supervision directly from the embedded feature space. Specifically, we project deep features into the embedding space to generate prototypes, each of which can be regarded as the category-level feature representation of a certain semantic category. These prototypes are then used to perform the pixelwise classification, with the advantage of capturing the global similarity throughout the whole pixels within the category. Moreover, to ensure accurate prototypes, we further introduce pixel-prototype contrast to better explore the discriminative category-level feature embedding. By integrating the guidance from the above pixel-level and category-level feature representations, the proposed algorithm obtains high-quality pseudolabels and extracts effective features. Extensive experiments on four RS image segmentation datasets have demonstrated the effectiveness of the proposed method. The code is available athttps://github.com/Duckyee728/PCSSS.git.

Multi-view learning can improve classification performance by combining information between different views. Due to the similarity in different views of the dataset, sometimes the features obtained are highly limited and redundant. At the same time, different views accumulate a large amount of noisy information, which will affect the classification performance of the model. To solve these problems, we embed privileged information in the model and introduce dictionary learning, and proposed a new dictionary-based multi-view learning method with privileged information (MVDL-PI). First, two sets of dictionaries (synthetic dictionary and analysis dictionary) and sparse representation matrices of different information domains are obtained for each view information and privilege information through dictionary learning. Then, we obtain consistency information from the regularization terms of the two different sets of synthetic dictionaries and construct a LUPI (Learning using privileged information) classifier by the sparse representation. In addition, we use alternating convex optimization and Lagrange multiplier methods to optimize the model and prove its convergence. In the experiment, we did a number of experiments comparing this method with similar recent methods. The experimental results show that the MVDL-PI method is superior to other methods in terms of stability and classification accuracy.