Recently, the generative retrieval paradigm has emerged as a transformative framework that significantly enhances the efficiency of large-scale industrial recommendation systems. This innovative approach systematically maps items to meaningful semantic identifiers (SIDs) and employs advanced sequence generation techniques to construct high-quality candidate sets, thereby enabling more accurate modeling of users' evolving interests and behavioral patterns. Nevertheless, two critical challenges remain inadequately addressed in current research: (1) Existing methodologies predominantly focus on modeling a single task such as predicting users' click behavior, while overlooking other tasks including predicting users' dwell-time and engagement behaviors, which are very important for video/content recommendation at the same time. The independent modeling of each task inevitably results in substantial computational overhead, thereby raising the pivotal question of whether the sophisticated multi-task learning capabilities inherent in LLMs can be effectively leveraged to achieve unified and efficient multi-task learning for generative retrieval. (2) The mapping mechanism from SIDs to concrete items requires substantial refinement to ensure precise and reliable retrieval performance. To tackle these issues, we propose RedGR, a generative retrieval model that unifies the modeling of multiple complex retrieval tasks. RedGR first applies the RQ-Kmeans algorithm to map items into SIDs, and then conducts pre-training on large-scale user behavior datasets to learn general knowledge. Then the RedGR model is finetuned on multi-task retrieval data with a unique instruction prompt for each task. This enables RedGR to generate the corresponding set of SIDs for each task. And the union of all sets of SIDs is the multi-task retrieval result. Finally, the Swing algorithm incorporates explicit, high-quality collaborative signals to strengthen the mapping from SIDs to specific items, thereby facilitating efficient retrieval of high-quality items. RedGR has been fully depolyed in the homefeed recommendation scenario of RedNote,serving hundreds of millions of users every day. Online A/B test results show a 0.178% increase in pagetime, a 0.734% increase in average user engagement, and a 0.076% growth in homefeed active users (FAU). These metrics collectively validate the superior performance of RedGR's unified retrieval modeling approach in complex multi-task scenarios.

Accurate watch time prediction is crucial for enhancing user engagement in streaming short-video platforms, although it is challenged by complex distribution characteristics across multi-granularity levels. Through systematic analysis of real-world industrial data, we uncover two critical challenges in watch time prediction from a distribution aspect: (1) coarse-grained skewness induced by a significant concentration of quick-skips1, (2) fine-grained diversity arising from various user-video interaction patterns. Consequently, we assume that the watch time follows the Exponential-Gaussian Mixture (EGM) distribution, where the exponential and Gaussian components respectively characterize the skewness and diversity. Accordingly, an Exponential-Gaussian Mixture Network (EGMN) is proposed for the parameterization of EGM distribution, which consists of two key modules: a hidden representation encoder and a mixture parameter generator. We conducted extensive offline experiments on public datasets and online A/B tests on the industrial short-video feeding scenario of Xiaohongshu App to validate the superiority of EGMN compared with existing state-of-the-art methods. Remarkably, comprehensive experimental results have proven that EGMN exhibits excellent distribution fitting ability across coarse-to-fine-grained levels. We open source related code on Github: https://github.com/BestActionNow/EGMN.

User-generated content (UGC) communities, especially those featuring multimodal content, improve user experiences by integrating visual and textual information into results (or items).The challenge of improving user experiences in complex systems with search and recommendation (S&R) services has drawn significant attention from both academia and industry these years.However, the lack of high-quality datasets has limited the research progress on multimodal S&R.To address the growing need for developing better S&R services, we present a novel multimodal information retrieval dataset in this paper, namely Qilin.The dataset is collected from Xiaohongshu, a popular social platform with over 300 million monthly active users and an average search penetration rate of over 70%.In contrast to existing datasets, Qilin offers a comprehensive collection of user sessions with heterogeneous results like image-text notes, video notes, commercial notes, and direct answers, facilitating the development of advanced multimodal neural retrieval models across diverse task settings.To better model user satisfaction and support the analysis of heterogeneous user behaviors, we also collect extensive APP-level contextual signals and genuine user feedback.Notably, Qilin contains user-favored answers and their referred results for search requests triggering the

While traditional distributionally robust optimization (DRO) aims to minimize the maximal risk over a set of distributions, Agarwal & Zhang (2022) recently proposed a variant that replaces risk with *excess risk*. Compared to DRO, the new formulation—minimax excess risk optimization (MERO) has the advantage of suppressing the effect of heterogeneous noise in different distributions. However, the choice of excess risk leads to a very challenging minimax optimization problem, and currently there exists only an inefficient algorithm for empirical MERO. In this paper, we develop efficient stochastic approximation approaches which directly target MERO. Specifically, we leverage techniques from stochastic convex optimization to estimate the minimal risk of every distribution, and solve MERO as a stochastic convex-concave optimization (SCCO) problem with biased gradients. The presence of bias makes existing theoretical guarantees of SCCO inapplicable, and fortunately, we demonstrate that the bias, caused by the estimation error of the minimal risk, is under-control. Thus, MERO can still be optimized with a nearly optimal convergence rate. Moreover, we investigate a practical scenario where the quantity of samples drawn from each distribution may differ, and propose a stochastic approach that delivers *distribution-dependent* convergence rates.

To deal with changing environments, adaptive regret has been proposed to minimize the regret over every interval. Previous studies have established a small-loss adaptive regret bound for general convex functions under the smoothness condition, offering the advantage of being much tighter than minimax rates for benign problems. However, it remains unclear whether similar bounds are attainable for other types of convex functions, such as exp-concave and strongly convex functions. In this paper, we first propose a novel algorithm that achieves a small-loss adaptive regret bound for exp-concave and smooth function. Subsequently, to address the limitation that existing algorithms can only handle one type of convex functions, we further design a universal algorithm capable of delivering small-loss adaptive regret bounds for general convex, exp-concave, and strongly convex functions simultaneously. That is challenging because the universal algorithm follows the meta-expert framework, and we need to ensure that upper bounds for both meta-regret and expert-regret are of small-loss types. Moreover, we provide a novel analysis demonstrating that our algorithms are also equipped with minimax adaptive regret bounds when functions are non-smooth.

Recent years have witnessed the booming of online social media platforms with embracing the popular service called “Time-Sync Comment”, which supports the viewers to share their time-sync opinions along with video content. In this way, we observe that numerous semantically-altered terms, or “Memes”, were created by niche users to express their unique ideas and emotions, and further attracted a large group of viewers with better activity and enthusiasm. Unfortunately, since the memes were created based on domain-specific knowledge and semantically varied depending on the multimodal context in videos, newcomers may fail to comprehend the semantic connotation of memes, which may severely impair their user-experiences. To deal with this issue, in this article, we propose a novel meme explanation framework, called ProMDE, to automatically capture and comprehend the memes in time-sync comments, which could further benefit the viewers with meme explanation service. Specifically, we first iteratively reconstruct the original time-sync comments compared with visual embedding to detect the semantically-altered terms as meme candidates. Afterward, based on the guides from the domain-specific corpus, visual and textual features will be fused to represent the context-aware multimodal cues. Moreover, to accurately describe the commonly-seen homophones in memes, i.e., they have the same pronunciation but different word-spelling expressions, we integrate the phonetic symbols as an additional modality to enhance the framework. Finally, we utilize a Transformer-based decoder to generate the natural language explanation for captured memes. Extensive experiments on a large real-world dataset prove that our framework could significantly outperform several state-of-the-art baseline methods, demonstrating the efficacy of modeling multimodal context and pronunciation for meme detection and explanation.