Autonomous vehicles often rely on high-definition (HD) maps for navigation; however, these maps are not frequently updated and often lack semi-static information, such as temporary roadwork zones, which can significantly alter the road network. This limitation underscores the urgent need for an accurate global position of roadwork zones. However, the absence of publicly available datasets for evaluating roadwork zone detection and geo-localization models has hindered the development of reliable autonomous driving systems. To address this challenge, we propose the Roadwork Zone Detection and Geo-localization (RZDG) dataset, which includes both simulated and real-world data, providing multimodal sensor inputs along with comprehensive annotations. The dataset supports multiple perception tasks, including image semantic segmentation, 3D object detection, and object geo-localization. In addition, we introduce a tracker-based roadwork zone detection and geo-localization (RZDG) pipeline, an extension of AB3DMOT, for accurate object geo-localization in roadwork zones. We benchmark our approach on the RZDG dataset, demonstrating its effectiveness in detecting roadwork zones and transforming object positions from the local coordinate system to the global coordinate system. A prediction is considered a true positive (TP) if its estimated position falls within one meter of the ground truth. Our experimental results show that our approach achieves high accuracy on both real and simulated data. Specifically, we report: Precision: 0.565 (real) / 0.615 (simulated) Recall: 0.898 (real) / 0.809 (simulated) F1-score: 0.597 (real) / 0.665 (simulated). The RZDG dataset and code can be found at: https://github.com/chrisyan/RZDG.

Enabling more concise and modular proofs is essential for advancing formal reasoning using interactive theorem provers (ITPs). Since many ITPs, such as Rocq and Lean, use tactic-style proofs, learning higher-level custom tactics is crucial for proof modularity and automation. This paper presents a novel approach to tactic discovery, which leverages Tactic Dependence Graphs (TDGs) to identify reusable proof strategies across multiple proofs. TDGs capture logical dependencies between tactic applications while abstracting away irrelevant syntactic details, allowing for both the discovery of new tactics and the refactoring of existing proofs into more modular forms. We have implemented this technique in a tool called TacMiner and compare it against an anti-unification-based approach ( Peano ) to tactic discovery. Our evaluation demonstrates that TacMiner can learn 3× as many tactics as Peano and reduces the size of proofs by 26% across all benchmarks. Furthermore, our evaluation demonstrates the benefits of learning custom tactics for proof automation, allowing a state-of-the-art proof automation tool to achieve a relative increase of 172% in terms of success rate.

Channel state information (CSI) is an essential aspect of the frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) system since there is no reciprocity between the bidirectional channels. However, the CSI transmission often requires significant channel resources because there may be hundreds of antennas transmitting and receiving data simultaneously. In this paper, we design an dissymmetric convolution neural network for CSI feedback (DiscoCSINet). Specifically, we utilize the dissymmetric convolution blocks (Disco-Blocks) to address the CSI compression and decompression issue, where convolution's feature extraction capability can be enhanced. To improve the storage efficiency of the receiver, we also employ a lightweight approach of the DiscoCSINet. Furthermore, we explore the fusion strategies of multi-rate and multi-scenario, respectively, and strengthen the generalization capability of the DiscoCSINet in practical settings. Experiment results indicate that the proposed DiscoCSINet can notably enhance the NMSE and cosine similarity$\rho$, especially in outdoor scenarios. Additionally, the proposed lightweight approach and multi-model fusion strategies can greatly decrease the parameter amounts by over 80% and 89%, respectively, but the performance are only slightly decayed.