Collaborative Filtering (CF) remains the cornerstone of modern recommender systems, with dense embedding-based methods dominating current practice. However, these approaches suffer from a critical limitation: our theoretical analysis reveals a fundamental Signal-to-Noise Ratio (SNR) ceiling when modeling unpopular items, where parameter-based dense models experience diminishing SNR under severe data sparsity. To overcome this bottleneck, we propose Sparse and Dense (SaD) , a unified framework that integrates the semantic expressiveness of dense embeddings with the structural reliability of sparse interaction patterns. We theoretically show that aligning these dual views yields a strictly superior global SNR. Concretely, SaD introduces a lightweight bidirectional alignment mechanism: the dense view enriches the sparse view by injecting semantic correlations, while the sparse view regularizes the dense model through explicit structural signals. Extensive experiments demonstrate that, under this dual-view alignment, even a simple matrix factorization–style dense model can achieve state-of-the-art performance. Moreover, SaD is plug-and-play and can be seamlessly applied to a wide range of existing recommender models, highlighting the enduring power of CF when leveraged from dual perspectives. Further evaluations on real-world benchmarks show that SaD consistently outperforms strong baselines, ranking first on the BarsMatch leaderboard ( https://openbenchmark.github.io/BARS/Matching/leaderboard/index.html ). The code is publicly available at https://github.com/harris26-G/SaD .

Social recommendation has been proven effective in addressing data sparsity in user–item interaction modeling by leveraging social networks. The recent integration of Graph Neural Networks (GNNs) has further enhanced prediction accuracy in contemporary social recommendation algorithms. However, many GNN-based approaches in social recommendation lack the ability to furnish meaningful explanations for their predictions. In this study, we confront this challenge by introducing SoREX, a self-explanatory GNN-based social recommendation framework. SoREX adopts a two-tower framework enhanced by friend recommendation, independently modeling social relations and user–item interactions, while jointly optimizing an auxiliary task to reinforce social signals. To offer explanations, we propose a novel ego-path extraction approach. This method involves transforming the ego-net of a target user into a collection of multi-hop ego-paths, from which we extract factor-specific and candidate-aware ego-path subsets as explanations. This process facilitates the summarization of detailed comparative explanations among different candidate items through intricate substructure analysis. Furthermore, we conduct explanation re-aggregation to explicitly correlate explanations with downstream predictions, imbuing our framework with inherent self-explainability. Comprehensive experiments conducted on four widely adopted benchmark datasets validate the effectiveness of SoREX in predictive accuracy. Additionally, qualitative and quantitative analyses confirm the effectiveness of the explanations extracted by SoREX. The corresponding code and data are available at https://github.com/antman9914/SoREX .

Privacy remains a significant challenge in public blockchain ecosystems. Mainstream add-on privacy solutions, such as Stealth Address Protocols (SAPs) and Zero-Knowledge Proof (ZKP)-based mixers, have recently attracted considerable attention. However, existing SAPs offer only ephemeral anonymity for users' transaction data, and their implementation and evaluation within the highly concurrent Unspent Transaction Output (UTXO) model remain largely unexplored. ZKP-based mixers are limited to native coin transfers with fixed denominations and require additional security assumptions, employing out-of-band encrypted channels to transmit notes. To overcome these challenges, we unify the core principles underlying both SAPs and ZKP mixers and formally introduce StealthHub, a UTXObased SAP. Compared with the widely adopted dual-key-based Umbra protocol prevalent on Ethereum Virtual Machine (EVM)-compatible chains, StealthHub reduces computational overhead for the prepare and scan announcements stages by over 71% and 32%, respectively. Furthermore, by leveraging Merkle Mountain Range (MMR) commitments and off-chain batch aggregation, our StealthHub implementation lowers deposit and shielded transfer transaction costs to approximately 76% of those for a standard transfer, substantially improving practical usability.

As large language models (LLMs) become increasingly integrated into applications serving users across diverse cultures, communities, and demographics, it is critical to align LLMs with pluralistic human values beyond average principles (e.g., HHH). In psychological and social value theories such as Schwartz’s Value Theory, pluralistic values are represented by multiple value dimensions paired with various priorities. However, existing methods encounter two challenges when aligning with such fine-grained value objectives: 1) they often treat multiple values as independent and equally important, ignoring their interdependence and relative priorities (value complexity); 2) they struggle to precisely control nuanced value priorities, especially those underrepresented ones (value steerability). To handle these challenges, we propose COUPLE, a COUnterfactual reasoning framework for PLuralistic valuE alignment. It introduces a structural causal model (SCM) to feature complex interdependency and prioritization among features, as well as the causal relationship between high-level value dimensions and behaviors. Moreover, it applies counterfactual reasoning to generate outputs aligned with any desired value objectives. Benefitting from explicit causal modeling, COUPLE also provides better interpretability. We evaluate COUPLE on two datasets with different value systems and demonstrate that COUPLE advances other baselines across diverse types of value objectives. Our code is available at https://github.com/microsoft/COUPLE.

Online platforms aggregate extensive user feedback across diverse behaviors, providing a rich source for enhancing user engagement. Traditional recommender systems, however, typically optimize for a single target behavior and represent user preferences with a single vector, limiting their ability to handle multiple equally important behaviors or diverse optimization objectives. This approach also struggles to capture the full spectrum of user interests, resulting in a narrow item pool during candidate generation. To address these limitations, we present Tricolore, a versatile multi-vector learning framework designed to uncover connections between various behavior types for more robust candidate generation. Tricolore's adaptive multi-task structure is customizable to specific platform needs. To manage the variability in sparsity across behavior types, we incorporate a behavior-wise multi-view fusion module that dynamically enhances learning. Additionally, a popularity-balanced strategy ensures the recommendation list balances accuracy with item popularity, fostering diversity and improving overall performance. Extensive experiments on public datasets demonstrate Tricolore's effectiveness in diverse recommendation scenarios, from short video platforms to e-commerce. Furthermore, by leveraging a shared base embedding strategy, Tricolore shows significant improvements, particularly for cold-start users. The source code is publicly available at: https://github.com/abnering/Tricolore