Dense retrieval has become a foundational paradigm in modern search systems, especially on short-video platforms. However, most industrial systems adopt a self-reinforcing training pipeline that relies on historically exposed user interactions for supervision. This paradigm inevitably leads to a filter bubble effect, where potentially relevant but previously unseen content is excluded from the training signal, biasing the model toward narrow and conservative retrieval. In this paper, we present CroPS (Cross-Perspective Positive Samples), a novel retrieval data engine designed to alleviate this problem by introducing diverse and semantically meaningful positive examples from multiple perspectives. CroPS enhances training with positive signals derived from user query reformulation behavior (query-level), engagement data in recommendation streams (system-level), and world knowledge synthesized by large language models (knowledge-level). To effectively utilize these heterogeneous signals, we introduce a Hierarchical Label Assignment (HLA) strategy and a corresponding H-InfoNCE loss that together enable fine-grained, relevance-aware optimization. Extensive experiments conducted on Kuaishou Search, a large-scale commercial short-video search platform, demonstrate that CroPS significantly outperforms strong baselines both offline and in live A/B tests, achieving superior retrieval performance and reducing query reformulation rates. CroPS is now fully deployed in Kuaishou Search, serving hundreds of millions of users daily.

Query auto-completion (QAC) plays a crucial role in modern search systems.However, in real-world applications, there are two pressing challenges that still need to be addressed.First, there is a need for hierarchical personalized representations for users.Previous approaches have typically used users' search behavior as a single, overall representation, which proves inadequate in more nuanced generative scenarios.Additionally, query prefixes are typically short and may contain typos or sensitive information, increasing the likelihood of generating toxic content compared to traditional text generation tasks.Such toxic content can degrade user experience and lead to public relations issues.Therefore, the second critical challenge is detoxifying QAC systems.Recent efforts to mitigate toxicity have involved generating queries unrelated to the given prefix, leading this approach still negatively impacts user experience.To address these two limitations, we propose a novel model (LaD) that captures personalized information from both long-term and short-term interests, incorporating adaptive detoxification.In LaD, personalized information is captured hierarchically at both coarse-grained and fine-grained levels.This approach preserves as much personalized information as possible while enabling online generation within time constraints.To move a further step, we propose an online training method based on Reject Preference Optimization (RPO).By incorporating a special token [Reject] during both the training and inference processes, the model achieves adaptive detoxification.Consequently, the generated text presented to users is both non-toxic and relevant to the given prefix.We conduct comprehensive experiments on industrial-scale datasets and perform online A/B tests, delivering the largest single-experiment metric improvement in nearly two years of our product.Our model has been deployed on Kuaishou search, driving the primary traffic

Massive MIMO can significantly improve diversity/multiplexing gain, channel capacity and spectrum efficiency. An efficient signal detection algorithm plays a very important role for system performance. However, the BER, complexity and delay performance of present signal detection algorithms are far from optimal with the increasing number of antennas. This paper presents an improved mixed Gibbs sampling algorithm based on multiple random parallel Markov chains (MGS-MRPMC). It has lower complexity than traditional signal detection algorithms in massive MIMO systems. The simulation shows that the proposed algorithm can alleviate the stalling problem encountered in the mixed Gibbs sampling (MGS) algorithm with higher order QAM. Moreover, it can reduce the serious delay of the mixed Gibbs sampling with multiple restarts (MGS-MR) algorithm. The use of parallel strategy makes it suitable for hardware implementation in practice.

Multiple-input multiple-output (MIMO) technology has been widely used as an efficient way to improve the capacity of wireless channels. As an optimal detection for MIMOOFDM systems, the maximum likelihood (ML) algorithm whose complexity rises exponentially with the number of transmit and receive antennas is not practical for real-time detection. Instead, the sphere decoding (SD) algorithm was proposed to find the solution to the ML detection problem, however, the complexity is still large. The choice of the initial radius for SD detector has a significant impact on the complexity. In this paper, an improved depth-first- search sphere decoding (IDFS) algorithm based on the optimization of likelihood ascent search (LAS) predetection is proposed. The simulation results demonstrate that the proposed algorithm can not only achieve almost the same performance as ML detector but also efficiently decrease the complexity. For example, for about 49 visiting nodes for 16QAM and 30 visiting nodes for 4QAM, IDFS algorithm has about 4dB SNR gain than Schnorr-Euchner sphere decoding (SESD) algorithm as Fig.5 shows.

Realistic power amplifier (PA) model plays a very important role in the energy efficiency analysis for relay system, since it takes up to 70% of the total power consumption. In this paper, we aim to investigate the impact of non-ideal PA on the optimal relay deployment for two-way relay system using amplify forward or decode forward protocol in comparison with that of ideal PA. In the two-way relay system, physical-layer network coding (PNC) is used to assist the relay communication. Taking both the realistic non-ideal PA and ideal PA into consideration, the closed-form expressions for the optimal energy-efficient relay deployment are derived. Relative numerical simulation results show that the impact of non-ideal PA on the optimal relay deployment is that it requires the relay node to be deployed nearer to base station (BS) than that with the ideal PA. Furthermore, the energy efficiency of the two-way relay system with non-ideal PA could be largely improved by applying the optimal relay deployment.