As new products are emerging daily, recommendation systems are required to quickly adapt to possible new domains without needing extensive retraining. This work presents ``X-Cross'' -- a novel cross-domain sequential-recommendation model that recommends products in new domains by integrating several domain-specific language models; each model is fine-tuned with low-rank adapters (LoRA). Given a recommendation prompt, operating layer by layer, X-Cross dynamically refines the representation of each source language model by integrating knowledge from all other models. These refined representations are propagated from one layer to the next, leveraging the activations from each domain adapter to ensure domain-specific nuances are preserved while enabling adaptability across domains. Using Amazon datasets for sequential recommendation, X-Cross achieves performance comparable to a model that is fine-tuned with LoRA, while using only 25% of the additional parameters. In cross-domain tasks, such as adapting from Toys domain to Tools, Electronics or Sports, X-Cross demonstrates robust performance, while requiring about 50%-75% less fine-tuning data than LoRA to make fine-tuning effective. Furthermore, X-Cross achieves significant improvement in accuracy over alternative cross-domain baselines. Overall, X-Cross enables scalable and adaptive cross-domain recommendations, reducing computational overhead and providing an efficient solution for data-constrained environments.

Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations. A fundamental challenge in CRSs lies in effectively understanding user preferences from conversations. User preferences can be multifaceted and complex, posing significant challenges for accurate recommendations even with access to abundant external knowledge. While interaction with users can clarify their true preferences, frequent user involvement can lead to a degraded user experience. To address this problem, we propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs. The simulated user provides feedback to the items recommended by CRSs, enabling them to better capture intricate user preferences through multi-turn interaction. Inspired by generative reward models, we design two types of feedback actions for the simulated user: i.e., generative item scoring, which offers coarse-grained feedback, and attribute-based item critique, which provides fine-grained feedback. To ensure seamless integration, these feedback actions are unified into an instruction-based format, allowing the development of a unified simulated user via instruction tuning on synthesized data. With this simulated user, automatic multi-turn interaction with CRSs can be effectively conducted. Furthermore, to strike a balance between effectiveness and efficiency, we draw inspiration from the paradigm of reward-guided search in complex reasoning tasks and employ beam search for the interaction process. On top of this, we propose an efficient candidate ranking method to improve the recommendation results derived from interaction. Extensive experiments on public datasets demonstrate the effectiveness, efficiency, and transferability of our approach.

Personalized food recommendation systems (Food-RecSys) critically underperform due to fragmented component understanding and the failure of conventional machine learning with vast, imbalanced food data. While Large Language Models (LLMs) offer promise, current generic Recommendation as Language Processing (RLP) strategies lack the necessary specialization for the food domain's complexity. This thesis tackles these deficiencies by first identifying and analyzing the essential components for effective Food-RecSys. We introduce two key innovations: a multimedia food logging platform for rich contextual data acquisition and the World Food Atlas, enabling unique geolocation-based food analysis previously unavailable. Building on this foundation, we pioneer the Food Recommendation as Language Processing (F-RLP) framework - a novel, integrated approach specifically architected for the food domain. F-RLP leverages LLMs in a tailored manner, overcoming the limitations of generic models and providing a robust infrastructure for effective, contextual, and truly personalized food recommendations.

With the rapid advancement of Multimodal Large Language Models (MLLMs), an increasing number of researchers are exploring their application in recommendation systems. However, the high latency associated with large models presents a significant challenge for such use cases. The EReL@MIR workshop provided a valuable opportunity to experiment with various approaches aimed at improving the efficiency of multimodal representation learning for information retrieval tasks. As part of the competition's requirements, participants were mandated to submit a technical report detailing their methodologies and findings. Our team was honored to receive the award for Task 2 - Winner (Multimodal CTR Prediction). In this technical report, we present our methods and key findings. Additionally, we propose several directions for future work, particularly focusing on how to effectively integrate recommendation signals into multimodal representations. The codebase for our implementation is publicly available at: https://github.com/Lattice-zjj/MMCTR_Code, and the trained model weights can be accessed at: https://huggingface.co/FireFlyCourageous/MMCTR_DIN_MicroLens_1M_x1.

Due to the convenience of mobile devices, the online games have become an important part for user entertainments in reality, creating a demand for friend recommendation in online games. However, none of existing approaches can effectively incorporate the multi-modal user features (e.g., images and texts) with the structural information in the friendship graph, due to the following limitations: (1) some of them ignore the high-order structural proximity between users, (2) some fail to learn the pairwise relevance between users at modality-specific level, and (3) some cannot capture both the local and global user preferences on different modalities. By addressing these issues, in this paper, we propose an end-to-end model FROG that better models the user preferences on potential friends. Comprehensive experiments on both offline evaluation and online deployment at Tencent have demonstrated the superiority of FROG over existing approaches.

Given the importance of these recommendation algorithms, it makes sense to try to design optimal ones. A basic criterion for optimality, that captures the first-order experience of users in a recommendation system, is to maximize the proportion of recommendations that are liked, 1 similar to [11, 23] The goal of this paper is to gain insight into the design of recommendation algorithms by finding a statistically optimal algorithm within the context of a natural model for recommendation systems. One of our findings is that the best way to obtain information about users and items in order to make good recommendations depends on the time horizon and its relation to various system parameters including the number of users, the diversity of users, and richness of the items; there are a number of operating regimes depending on these parameters. It goes without saying that the nature of any insight obtained is intertwined with the choice of model. We use the same model as [11], closely related to those studied in [10, 12]. The model is different from those in other papers on the topic; we now motivate its key features.

Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation Xiang Li a,, Haixu Ma a,, Guanyong Wu a, Shi Mu a, Chen Li a, and Shunpan Liang a,b, a School of Information Science and Engineering, Yanshan University, Qin Huangdao, 066004, China b Xinjiang College Of Science & Technology, Korla, 841000, ChinaA R T I C L E I N F OKeywords: Medication Recommendation Molecular Representation Learning A B S T R A C T Medication recommendation is crucial in healthcare, offering effective treatments based on patient's electronic health records (EHR). Previous studies show that integrating more medication-related knowledge improves medication representation accuracy. However, not all medications encompass multiple types of knowledge data simultaneously. For instance, some medications provide only textual descriptions without structured data. This imbalance in data availability limits the performance of existing models, a challenge we term the "bucket effect" in medication recommendation. To fill this gap, we introduce a cross-modal medication encoder capable of seamlessly aligning data from different modalities and propose a medication recommendation framework to integrate Multiple types of K nowledge, named MKMed. Then, we combine the multi-knowledge medication representations with patient records for recommendations. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that MKMed mitigates the "bucket effect" in data, and significantly outperforms state-of-the-art baselines in recommendation accuracy and safety.1. Introduction Given the increasing demand for healthcare resources, there is a growing emphasis on AI-based medical systems. Medication recommendations Shang, Xiao, Ma, Li and Sun (2019); Wu, Qiu, Jiang, Qi and Wu (2022); Li, Liang, Hou and Ma (2024a), as a key area, aim to integrate clinical knowledge with patient electronic health records (EHR), enhancing the accuracy, safety, and efficiency of clinical decision-making for patients. Existing methods can be divided into two categories. The first category focuses on exploring the complex relationships between multiple medical events, optimizing patient representation by constructing complex networksLe, Tran and Venkatesh (2018); Jin, Yang, Sun, Liu, Qu and Tong (2018); Zheng, Wang, Xu, Shen, Qin, Huai, Liu and Chen (2021). For example, RAREMed Zhao, Jing, Feng, Wu, Gao and He (2024) focuses on the connections between rare events and others.

Fashion styling and personalized recommendations are pivotal in modern retail, contributing substantial economic value in the fashion industry. With the advent of vision-language models (VLM), new opportunities have emerged to enhance retailing through natural language and visual interactions. This work proposes FashionM3, a multimodal, multitask, and multiround fashion assistant, built upon a VLM fine-tuned for fashion-specific tasks. It helps users discover satisfying outfits by offering multiple capabilities including personalized recommendation, alternative suggestion, product image generation, and virtual try-on simulation. Fine-tuned on the novel FashionRec dataset, comprising 331,124 multimodal dialogue samples across basic, personalized, and alternative recommendation tasks, FashionM3 delivers contextually personalized suggestions with iterative refinement through multiround interactions. Quantitative and qualitative evaluations, alongside user studies, demonstrate FashionM3's superior performance in recommendation effectiveness and practical value as a fashion assistant.

If you've been keeping up with the recent discussion around how best to use Signal and how to keep journalists out of your private chats about national security matters, you'll know that White House officials have been blaming an iPhone feature called Siri Suggestions for adding unauthorized members to a private group chat. Siri Suggestions works on iPhones (and iPads and Macs) to give you contextually aware assistance when you need it. The feature might make suggestions about who to invite to events based on previous events, for example, or give you prompts for searches on your device, based on what you've searched for at certain times in the past. In the case of the White House Signal chat blunders, it appears Siri made a contact suggestion based on details included in an email--only the contact details in the email weren't those of the email sender but those of someone mentioned in the message, which is where the confusion arose. As with many modern day AI tools, Siri Suggestions lets you choose where to draw the line on how much assistance to get.

Google just announced that it will soon drop support for the first- and second-generation Nest Learning Thermostats. The devices won't stop working completely, but remote access is going away, as are software updates and compatibility with the Google Home app. The older Nest Learning Thermostats that are losing support include the second-generation units for the U.S., released in 2014, as well as the European version of the second-gen thermostat, which also went on sale in 2014. The original Nest Learning Thermostat, which was released only in the U.S., landed in 2011. Google says it will drop support for the thermostats starting October 25, 2025. Besides no longer receiving software updates, the older Nest Leaning thermostats will lose Nest and Google Home app support, meaning no more out-of-home control.