Existing end-to-end approaches of robotic manipulation often lack generalization to unseen objects or tasks due to limited data and poor interpretability. While recent Multimodal Large Language Models (MLLMs) demonstrate strong commonsense reasoning, they struggle with geometric and spatial understanding required for pose prediction. In this paper, we propose RobMRAG, a 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation (MRAG) framework for zero-shot robotic manipulation. Specifically, We construct a multi-source manipulation knowledge base containing object contact frames, task completion frames, and pose parameters. During inference, a Hierarchical Multimodal Retrieval module first employs hybrid semantic search to find task-relevant object prototypes, then selects the geometrically closest reference example based on pixel-level similarity and Instance Matching Distance (IMD). We further introduce a 3D-Aware Pose Refinement module based on 3D Gaussian Splatting into the MRAG framework, which aligns the pose of the reference object to the target object in 3D space. The aligned results are reprojected onto the image plane and used as input to the MLLM to enhance the generation of the final pose parameters. Extensive experiments show that on a test set containing 30 categories of household objects, our method improves the success rate by 7.76% compared to the best-performing zero-shot baseline under the same setting, and by 6.54% compared to the state-of-the-art supervised baseline. Our results validate that RobMRAG effectively bridges the gap between high-level semantic reasoning and low-level geometric execution, enabling robotic systems that generalize to unseen objects while remaining inherently interpretable.

Polynomial multiplication is one of the most computationally intensive operations in lattice-based cryptographic systems, directly impacting overall computational efficiency. Although the Number Theoretic Transform (NTT) reduces the time complexity of polynomial multiplication fromO(n2) toO(nlogn), the varying parameter requirements of different lattice algorithms limit the generality of hardware designs. To address this issue, we propose an innovative hardware architecture that tightly couples the NTT unit with the Load and Store Unit (LSU) in the pipeline of a RISC-V processor. We also propose a hybrid width data path method that effectively reduces data transfer time. Compared to previous designs, our architecture minimizes data transfer latency while enhancing computational flexibility and scalability. Specifically, we have customized NTT-related instructions to support Inverse Number Theoretic Transform (INTT) and various NTT parameter configurations. Experimental results demonstrate that our solution significantly shortens the NTT computation cycle, achieving over 10× speedup compared to software implementations. In comparison to existing solutions, our architecture exhibits superior area-time product (ATP) performance.

Multimodal Large Language Models have made significant strides in integrating visual and textual information, yet they often struggle with effectively aligning these modalities. We introduce a novel image tokenizer that bridges this gap by applying the principle of Byte-Pair Encoding (BPE) to visual data. Unlike conventional approaches that rely on separate visual encoders, our method directly incorporates structural prior information into image tokens, mirroring the successful tokenization strategies used in text-only Large Language Models. This innovative approach enables Transformer models to more effectively learn and reason across modalities. Through theoretical analysis and extensive experiments, we demonstrate that our BPE Image Tokenizer significantly enhances MLLMs' multimodal understanding capabilities, even with limited training data. Leveraging this method, we develop Being-VL-0, a model that demonstrates superior performance across various benchmarks and shows promising scalability, potentially paving the way for more efficient and capable multimodal foundation models. For further details, visit our website https://github.com/BeingBeyond/Being-VL-0.

Mobile crowdsensing (MCS) utilizes sensors distributed across different vehicles to support intelligent transportation and environmental monitoring. Recently, most of the research on MCS in Internet of Vehicles (IoV) mainly focuses on privacy protection and data security of anonymous authentication, but there are still shortcomings in reliability evaluation and reputation management of sensing vehicles. Besides, the lack of effective management of identity information may lead to difficulties in tracking malicious behavior. In this article, we propose a blockchain-assisted anonymous authentication and reputation management (BARM) scheme for MCS in IoV. Specifically, an efficient anonymous authentication algorithm is proposed for sensing vehicles. Then, the privacy protection reputation evaluation algorithm is proposed to ensure the reliability of the sensing vehicles and the security of sensing data. Meanwhile, an accurate reputation update algorithm is proposed to effectively check and update the reputation values of participating sensing vehicles. Besides, the smart contracts are written and deployed on the blockchain to manage the information of the sensing vehicles, which improves the security, efficiency, and trust of the identity management. Subsequently, a formal security verification method based on colored petri net (CPN) and Dolev-Yao attacker model is proposed to evaluate the security of the scheme. The evaluation results show that the scheme can effectively resist a variety of different types of attacks and has multiple security attributes. Performance analysis shows that the proposed scheme has low computation and communication overheads and high robustness.