Conventional recommendation systems frequently fail to fully exploit the high-dimensional semantic signals inherent in multimedia content, thereby limiting the fidelity of user preference modeling. While Multimodal Large Language Models (MM-LLMs) offer robust mechanisms for interpreting such complex data, their integration into latency-constrained, industrial-scale architectures remains a significant challenge. To address this, we propose a generalized framework for MM-LLM-driven multimedia understanding. Our methodology employs a tripartite architecture encompassing content interpretation, representation extraction, and systematic pipeline integration, instantiated via a LLaMA2-based model that generates descriptive captions subsequently ingested as tokenized categorical features. Empirical evaluation demonstrates the efficacy of this approach, yielding a 0.35% increase in offline AUC and a 0.02% improvement in online metrics at scale, substantiating the practical viability of leveraging MM-LLMs to enhance large-scale recommendation performance.

Higher-order staircase codes form a class of generalized staircase codes in which each bit is protected by more than two component codes. Among them, the extended-Hamming-based higher-order staircase codes are promising candidates for applications that require high coding rate, low error floor, and low decoding complexity. Despite their potential, their performance is still limited by conventional decoding methods, and the structural properties of their minimum stall patterns are not fully understood. To address these issues, we first introduce a novel soft-aided bounded distance decoder (SA-BDD) based on constrained bit flipping (CBF), denoted as SA-BDD-CBF, which demonstrates an effective performance–complexity–latency tradeoff of the extended-Hamming-based higher-order staircase codes. With appropriate parameter, the complexity of SA-BDDCBF is at most 3.4 times that of BDD. This is significantly lower than those of the multiply-chained zipper code and the traditional staircase code, which require approximately 31 and 39 times the complexity of BDD, respectively. Meanwhile, its performance gaps to the comparable multiply-chained zipper code and the traditional staircase code is only 0.10–0.15 dB, demonstrating an effective trade-off between decoding complexity and performance. We then establish several properties of the stall patterns and leverage these properties to develop efficient algorithms to search for both intra- and inter-block stall patterns. These algorithms provide exact values or upper bounds on the minimum sizes of the stall patterns. Extensive simulation results confirm the advantages of the proposed SA-BDD-CBF. In particular, it achieves a gain of 0.4 dB, while the associated increase in complexity remains acceptable for practical deployment. Moreover, the searching algorithms determine the exact minimum sizes of the stall patterns for block sizes up to 10 and obtain upper bounds for block sizes larger than 10. These findings advance the practical deployment of higher-order staircase codes in future high-throughput communication systems.

In this paper, we introduce the Generalized Auto Segmentation (GAS), an end-to-end, cross-domain personalization platform developed at Meta. GAS is designed to optimize personalization policies for online experiments, operating independently of any specific server infrastructure. Our process begins with a seed experiment to collect user data, which is followed by feature logging and selection. User segmentation is then performed using a feature-threshold method. Specifically, we utilize simple combinations of single or dual features to identify concise, explainable, and sustainable user cohorts that enhance both business outcomes and user experience over the long term. Treatments and the reward function for these segments are refined through ParallAX, a novel methodology at Meta that uses offline estimates to optimize online metrics, ensuring impactful and precisely tailored interventions for diverse user groups. The deployment of GAS across various Meta productions has demonstrated its efficiency and effectiveness.

Abstract With the development of 5G technology, the short delay requirements of commercialization and large amounts of data change our lifestyle day-to-day. In this background, this paper proposes a fast blind deblurring algorithm for QR code images, which mainly achieves the effect of adaptive scale control by introducing an evaluation mechanism. Its main purpose is to solve the out-of-focus caused by lens shake, inaccurate focus, and optical noise by speeding up the latent image estimation in the process of multi-scale division iterative deblurring. The algorithm optimizes productivity under the guidance of collaborative computing, based on the characteristics of the QR codes, such as the features of gradient and strength. In the evaluation step, the Tenengrad method is used to evaluate the image quality, and the evaluation value is compared with the empirical value obtained from the experimental data. Combining with the error correction capability, the recognizable QR codes will be output. In addition, we introduced a scale control parameter to study the relationship between the recognition rate and restoration time. Theoretical analysis and experimental results show that the proposed algorithm has high recovery efficiency and well recovery effect, can be effectively applied in industrial applications.

In recent years, online shopping is becoming more and more popular. Users type keyword queries on product search systems to find relevant products, accessories, and even related products. However, existing product search systems always return very similar products on the first several pages instead of taking diversity into consideration. In this paper, we propose a novel approach to address the diversity issue in the context of product search. We transform search result diversification into a combination of diversifying product categories and diversifying product attribute values within each category. The two sub-problems are optimization problems which can be reduced into well-known NP-hard problems respectively. We further leverage greedy-based approximation algorithms for efficient product search results re-ranking.