To address the high complexity and noise sensitivity of the Temporal Multiple Sparse Bayesian Learning (TMSBL) algorithm in shallow-sea environments, this paper proposes a novel and robust channel estimation scheme. Our proposed scheme first denoises the received pilot matrix using the K-Singular Value Decomposition (KSVD) algorithm and then leverages the Stagewise Orthogonal Matching Pursuit (StOMP) to acquire a robust sparse prior to initializing the TMSBL framework. This structured approach leverages the temporal correlation between channels for joint estimation, while noise variance is estimated directly from OFDM null subcarriers to enhance stability and efficiency. The simulation results demonstrate the superiority of the proposed method. At an SNR of -10 dB, it reduces the normalized mean square error (NMSE) by more than 94% compared to the standard TMSBL algorithm and reduces the computation time by approximately 95.87%, ensuring higher accuracy and efficiency for underwater acoustic communications.

In interactive point cloud segmentation, users can achieve higher accuracy object masks than in instance segmentation by performing limited positive and/or negative clicks on the objects of interest in the scene. Existing methods often employ sparse click representations, leading the model to focus more on local detail features around the click points and failing to fully exploit the guidance information provided by each click, thus impacting the click effectiveness. We utilize a dense representation that reflects spatial distance relationships, known as the distance map, as the click channel to tackle the sparsity problem of click representation in current approaches. Based on the distance map, we introduce ClickEnhance, which is designed to maximize the guiding impact of each click. The proposed method encompasses the design of a click-specific encoder and the utilization of contrastive learning. The Click-Specific Encoder ensures that the network can adequately consider the influence of individual clicks during the feature encoding phase. Contrastive learning, on the other hand, reduces the feature distance between the click points and the target object, thus simplifying the subsequent segmentation process. Experimental results demonstrate that the ClickEnhance method markedly improves segmentation performance across multiple datasets, exhibiting superior generalization capabilities on challenging datasets compared to the state-of-the-art methods. This allows for the generation of high-precision object-level masks with fewer interactions, indicating great potential for practical applications.

Dexterous grasping is a fundamental yet challenging skill in robotic manipulation, requiring precise interaction between robotic hands and objects. In this paper, we present$\mathcal{D}(\mathcal{R}, \mathcal{O})$Grasp, a novel framework that models the interaction between the robotic hand in its grasping pose and the object, enabling broad generalization across various robot hands and object geometries. Our model takes the robot hand's description and object point cloud as inputs and efficiently predicts kinematically valid and stable grasps, demonstrating strong adaptability to diverse robot embodiments and object geometries. Extensive experiments conducted in both simulated and real-world environments validate the effectiveness of our approach, with significant improvements in success rate, grasp diversity, and inference speed across multiple robotic hands. Our method achieves an average success rate of$87.53\%$in simulation in less than one second, tested across three different dexterous robotic hands. In real-world experiments using the LeapHand, the method also demonstrates an average success rate of$\mathbf{8 9\%}. \mathcal{D}(\mathcal{R}, \mathcal{O})$Grasp provides a robust solution for dexterous grasping in complex and varied environments. The code, appendix, and videos are available on our project website at https://nus-lins-lab.github.io/drograspweb/.

Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. In this paper, we present MetaFold, a unified framework that disentangles task planning from action prediction and learns each independently to enhance model generalization. It employs language-guided point cloud trajectory generation for task planning and a low-level foundation model for action prediction. This structure facilitates multi-category learning, enabling the model to adapt flexibly to various user instructions and folding tasks. We also construct a large-scale MetaFold dataset comprising folding point cloud trajectories for a total of 1210 garments across multiple categories, each paired with corresponding language annotations. Extensive experiments demonstrate the superiority of our proposed framework. Supplementary materials are available on our website: https://meta-fold.github.io/.

Recent studies on Vision-Language-Action (VLA) models have shifted from the end-to-end action-generation paradigm toward a pipeline involving task planning followed by action generation, demonstrating improved performance on various complex, long-horizon manipulation tasks. However, existing approaches vary significantly in terms of network architectures, planning paradigms, representations, and training data sources, making it challenging for researchers to identify the precise sources of performance gains and determine which component is more difficult to learn. To systematically investigate the impacts of different planning paradigms and representations isolating from network architectures and training data, in this paper, we introduce \name, a unified VLA architecture suite capable of various task planning paradigms, and design a comprehensive suite of controlled experiments across diverse object categories (rigid and deformable), visual modalities (2D and 3D), environments (simulation and real-world), and end-effectors (grippers and dexterous hands). Our results demonstrate that: 1) visually grounded planning representations are generally better than language planning representations; 2) the Hierarchical-VLA paradigm generally achieves superior performance than other paradigms, albeit at the cost of slower training and inference speeds.

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause extrapolation error in the learning process. In many robotic applications, an inaccurate simulator is often available. However, the data directly collected from the inaccurate simulator cannot be directly used in offline RL due to the well-known exploration-exploitation dilemma and the dynamic gap between inaccurate simulation and the real environment. To address these issues, we propose a novel approach to combine the offline dataset and the inaccurate simulation data in a better manner. Specifically, we pre-train a generative adversarial network (GAN) model to fit the state distribution of the offline dataset. Given this, we collect data from the inaccurate simulator starting from the distribution provided by the generator and reweight the simulated data using the discriminator. Our experimental results in the D4RL benchmark and a real-world manipulation task confirm that our method can benefit more from both inaccurate simulator and limited offline datasets to achieve better performance than the state-of-the-art methods.

The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations for particular tasks. However, building the feature extraction component for such systems requires extensive domain-specific expertise or data. The exceptionally rapid development of foundation models is likely to usher in newfound abilities in such intelligent sensing. We propose a new scheme for sensing model, which we refer to as semi-generalist sensing model (SGSM). SGSM is able to semiautomatically solve various tasks using relatively less task-specific labeled data compared to traditional systems. Built through the analysis of the common theoretical model, SGSM can depict different modalities, such as the acoustic and Wi-Fi signal. Experimental results on such two heterogeneous sensors illustrate that SGSM functions across a wide range of scenarios, thereby establishing its broad applicability. In some cases, SGSM even achieves better performance than sensor-specific specialized solutions. Wi-Fi evaluations indicate a 20% accuracy improvement when applying SGSM to an existing sensing model.

Due to challenges around low-quality comments and misinformation, many news outlets have opted to turn off commenting features on their websites. The New York Times (NYT), on the other hand, has continued to scale up its online discussion resources to reach large audiences. Through interviews with the NYT moderation team, we present examples of how moderators manage the first ~24 hours of online discussion after a story breaks, while balancing concerns about journalistic credibility. We discuss how managing comments at the NYT is not merely a matter of content regulation, but can involve reporting from the "community beat" to recognize emerging topics and synthesize the multiple perspectives in a discussion to promote community. We discuss how other news organizations---including those lacking moderation resources---might appropriate the strategies and decisions offered by the NYT. Future research should investigate strategies to share and update the information generated about topics in the news through the course of content moderation.