Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations

Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, and presentation. To address these limitations, we introduce Xinyu AI Search, a novel system that incorporates a query-decomposition graph to dynamically break down complex queries into sub-queries, enabling stepwise retrieval and generation. Our retrieval pipeline enhances diversity through multi-source aggregation and query expansion, while filtering and re-ranking strategies optimize passage relevance. Additionally, Xinyu AI Search introduces a novel approach for fine-grained, precise built-in citation and innovates in result presentation by integrating timeline visualization and textual-visual choreography. Evaluated on recent real-world queries, Xinyu AI Search outperforms eight existing technologies in human assessments, excelling in relevance, comprehensiveness, and insightfulness. Ablation studies validate the necessity of its key sub-modules. Our work presents the first comprehensive framework for generative AI search engines, bridging retrieval, generation, and user-centric presentation.

URLLC and eMBB Coexistence in MIMO Non-orthogonal Multiple Access Systems

Enhanced mobile broadband (eMBB) and ultrareliable and low-latency communications (URLLC) are two major expected services in the fifth-generation mobile communication systems (5G). Specifically, eMBB applications support extremely high data rate communications, while URLLC services aim to provide stringent latency with high reliability communications. Due to their differentiated quality-of-service (QoS) requirements, the spectrum sharing between URLLC and eMBB services becomes a challenging scheduling issue. In this paper, we aim to investigate the URLLC and eMBB coscheduling/coexistence problem under a puncturing technique in multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) systems. The objective function is formulated to maximize the data rate of eMBB users while satisfying the latency requirements of URLLC users through joint user selection and power allocation scheduling. To solve this problem, we first introduce an eMBB user clustering mechanism to balance the system performance and computational complexity. Thereafter, we decompose the original problem into two subproblems, namely the scheduling problem of user selection and power allocation. We introduce a Gale-Shapley (GS) theory to solve with the user selection problem, and a successive convex approximation (SCA) and a difference of convex (D.C.) programming to deal with the power allocation problem. Finally, an iterative algorithm is utilized to find the global solution with low computational complexity. Numerical results show the effectiveness of the proposed algorithms, and also verify the proposed approach outperforms other baseline methods.