In this paper, we present the findings of a user study that evaluated the social acceptance of eXtended Reality (XR) agent technology, focusing on a remotely accessible, web-based XR training system developed for journalists. This system involves user interaction with a virtual avatar, enabled by a modular toolkit. The interactions are designed to provide tailored training for journalists in digital-remote settings, especially for sensitive or dangerous scenarios, without requiring specialized end-user equipment like headsets. Our research adapts and extends the Almere model, representing social acceptance through existing attributes such as perceived ease of use and perceived usefulness, along with added ones like dependability and security in the user-agent interaction. The XR agent was tested through a controlled experiment in a real-world setting, with data collected on users' perceptions. Our findings, based on quantitative and qualitative measurements involving questionnaires, contribute to the understanding of user perceptions and acceptance of XR agent solutions within a specific social context, while also identifying areas for the improvement of XR systems.

In the era of big data applications, Federated Graph Learning (FGL) has emerged as a prominent solution that reconcile the tradeoff between optimizing the collective intelligence between decentralized datasets holders and preserving sensitive information to maximum. Existing FGL surveys have contributed meaningfully but largely focus on integrating Federated Learning (FL) and Graph Machine Learning (GML), resulting in early stage taxonomies that emphasis on methodology and simulated scenarios. Notably, a data centric perspective, which systematically examines FGL methods through the lens of data properties and usage, remains unadapted to reorganize FGL research, yet it is critical to assess how FGL studies manage to tackle data centric constraints to enhance model performances. This survey propose a two-level data centric taxonomy: Data Characteristics, which categorizes studies based on the structural and distributional properties of datasets used in FGL, and Data Utilization, which analyzes the training procedures and techniques employed to overcome key data centric challenges. Each taxonomy level is defined by three orthogonal criteria, each representing a distinct data centric configuration. Beyond taxonomy, this survey examines FGL integration with Pretrained Large Models, showcases realistic applications, and highlights future direction aligned with emerging trends in GML.

Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs) show promise in this direction, their scalability in recommender systems is limited by high costs and latency. Retrieval-based approaches using smaller language models mitigate these issues but often rely on single-modal item representations, overlook long-term user preferences, and require full model retraining, posing challenges for real-world deployment. In this paper, we present JAM (Just Ask for Music), a lightweight and intuitive framework for natural language music recommendation. JAM models user-query-item interactions as vector translations in a shared latent space, inspired by knowledge graph embedding methods like TransE. To capture the complexity of music and user intent, JAM aggregates multimodal item features via cross-attention and sparse mixture-of-experts. We also introduce JAMSessions, a new dataset of over 100k user-query-item triples with anonymized user/item embeddings, uniquely combining conversational queries and user long-term preferences. Our results show that JAM provides accurate recommendations, produces intuitive representations suitable for practical use cases, and can be easily integrated with existing music recommendation stacks.

Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate personalized item sequences. However, their adoption is hindered by (1) the lack of explicit information for token reasoning, (2) high computational costs due to quadratic attention complexity and dense sequence representations after tokenization, and (3) limited multi-scale modeling over user history. In this work, we propose GRACE (Generative Recommendation via journey-aware sparse Attention on Chain-of-thought tokEnization), a novel generative framework for multi-behavior sequential recommendation. GRACE introduces a hybrid Chain-of-Thought (CoT) tokenization method that encodes user-item interactions with explicit attributes from product knowledge graphs (e.g., category, brand, price) over semantic tokenization, enabling interpretable and behavior-aligned generation. To address the inefficiency of standard attention, we design a Journey-Aware Sparse Attention (JSA) mechanism, which selectively attends to compressed, intra-, inter-, and current-context segments in the tokenized sequence. Experiments on two real-world datasets show that GRACE significantly outperforms state-of-the-art baselines, achieving up to +106.9% HR@10 and +106.7% NDCG@10 improvement over the state-of-the-art baseline on the Home domain, and +22.1% HR@10 on the Electronics domain. GRACE also reduces attention computation by up to 48% with long sequences.

Next point of interest (POI) recommendation primarily predicts future activities based on users' past check-in data and current status, providing significant value to users and service providers. We observed that the popular check-in times for different POI categories vary. For example, coffee shops are crowded in the afternoon because people like to have coffee to refresh after meals, while bars are busy late at night. However, existing methods rarely explore the relationship between POI categories and time, which may result in the model being unable to fully learn users' tendencies to visit certain POI categories at different times. Additionally, existing methods for modeling time information often convert it into time embeddings or calculate the time interval and incorporate it into the model, making it difficult to capture the continuity of time. Finally, during POI prediction, various weighting information is often ignored, such as the popularity of each POI, the transition relationships between POIs, and the distances between POIs, leading to suboptimal performance. To address these issues, this paper proposes a novel next POI recommendation framework called Graph Disentangler with POI Weighted Module (GDPW). This framework aims to jointly consider POI category information and multiple POI weighting factors. Specifically, the proposed GDPW learns category and time representations through the Global Category Graph and the Global Category-Time Graph. Then, we disentangle category and time information through contrastive learning. After prediction, the final POI recommendation for users is obtained by weighting the prediction results based on the transition weights and distance relationships between POIs. We conducted experiments on two real-world datasets, and the results demonstrate that the proposed GDPW outperforms other existing models, improving performance by 3% to 11%.

Recommender systems are known to exhibit fairness issues, particularly on the product side, where products and their associated suppliers receive unequal exposure in recommended results. While this problem has been widely studied in traditional recommendation settings, its implications for bundle recommendation (BR) remain largely unexplored. This emerging task introduces additional complexity: recommendations are generated at the bundle level, yet user satisfaction and product (or supplier) exposure depend on both the bundle and the individual items it contains. Existing fairness frameworks and metrics designed for traditional recommender systems may not directly translate to this multi-layered setting. In this paper, we conduct a comprehensive reproducibility study of product-side fairness in BR across three real-world datasets using four state-of-the-art BR methods. We analyze exposure disparities at both the bundle and item levels using multiple fairness metrics, uncovering important patterns. Our results show that exposure patterns differ notably between bundles and items, revealing the need for fairness interventions that go beyond bundle-level assumptions. We also find that fairness assessments vary considerably depending on the metric used, reinforcing the need for multi-faceted evaluation. Furthermore, user behavior plays a critical role: when users interact more frequently with bundles than with individual items, BR systems tend to yield fairer exposure distributions across both levels. Overall, our findings offer actionable insights for building fairer bundle recommender systems and establish a vital foundation for future research in this emerging domain.

Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-start problem. An empirical analysis of DCRS and statistics on the REDIAL corpus show that only 10% of head movies account for nearly half of all mentions, whereas about 70% of tail movies receive merely 26% of the attention. This imbalance gives rise to three critical challenges: head over-fitting, body representation drift, and tail sparsity. To address these issues, we propose LumiCRS, an end-to-end framework that mitigates long-tail imbalance through three mutually reinforcing layers: (i) an Adaptive Comprehensive Focal Loss (ACFL) that dynamically adjusts class weights and focusing factors to curb head over-fitting and reduce popularity bias; (ii) Prototype Learning for Long-Tail Recommendation, which selects semantic, affective, and contextual prototypes to guide clustering and stabilize body and tail representations; and (iii) a GPT-4o-driven prototype-guided dialogue augmentation module that automatically generates diverse long-tail conversational snippets to alleviate tail sparsity and distribution shift. Together, these strategies enable LumiCRS to markedly improve recommendation accuracy, diversity, and fairness: on the REDIAL and INSPIRED benchmarks, LumiCRS boosts Recall@10 and Tail-Recall@10 by 7-15% over fifteen strong baselines, while human evaluations confirm superior fluency, informativeness, and long-tail relevance. These results demonstrate the effectiveness of multi-layer collaboration in building an efficient and fair long-tail conversational recommender.

TL;DR: A lifetime license of SwifDoo PDF Pro for Windows is now just 29.97 ( 129.00). Ever had that recurring nightmare that you're running and you can't get anywhere? It's like being on a treadmill that you can't get off, tiring yourself out until you wake up covered in sweat. No joke, that's what doing PDF paperwork feels like. Anyone with a laptop job (or literally any job that requires you to open a laptop and fill out documents or forms) understands that the second you dig into the figurative pile of paperwork in your emails, more comes to replace it.

Zohran Mamdani gave Hinge an unofficial boost last month when the New York mayoral candidate revealed that he met his wife, Rama Duwaji, through swiping. "There is still hope on those dating apps," he said on the Bulwark podcast a week before his stunning victory in the Democratic primary. The tidbit spread over social media, cementing the 33-year-old democratic socialist's status as a millennial everyman. A subsequent Cosmopolitan headline read: "Zohran Mamdani could make history (as the first NYC mayor to meet his wife on Hinge)." Representatives for Hinge would not comment, but plenty of eligible New Yorkers did, claiming they would redownload the app due to Mamdani's success, in spite of their dating fatigue.

The modern recommender systems are facing an increasing challenge of modelling and predicting the dynamic and context-rich user preferences. Traditional collaborative filtering and content-based methods often struggle to capture the temporal patternings and evolving user intentions. While Large Language Models (LLMs) have gained gradual attention in recent years, by their strong semantic understanding and reasoning abilities, they are not inherently designed to model chronologically evolving user preference and intentions. On the other hand, for sequential models like LSTM (Long-Short-Term-Memory) which is good at capturing the temporal dynamics of user behaviour and evolving user preference over time, but still lacks a rich semantic understanding for comprehensive recommendation generation. In this study, we propose DUALRec (Dynamic User-Aware Language-based Recommender), a novel recommender that leverages the complementary strength of both models, which combines the temporal modelling abilities of LSTM networks with semantic reasoning power of the fine-tuned Large Language Models. The LSTM component will capture users evolving preference through their viewing history, while the fine-tuned LLM variants will leverage these temporal user insights to generate next movies that users might enjoy. Experimental results on MovieLens-1M dataset shows that the DUALRec model outperforms a wide range of baseline models, with comprehensive evaluation matrices of Hit Rate (HR@k), Normalized Discounted Cumulative Gain (NDCG@k), and genre similarity metrics. This research proposes a novel architecture that bridges the gap between temporal sequence modeling and semantic reasoning, and offers a promising direction for developing more intelligent and context-aware recommenders.