Frozen Large Video Language Models (LVLMs) are increasingly employed in micro-video recommendation (MVR) due to their strong multimodal understanding. However, existing apporches typically deploy LVLMs as fixed black-box feature extractors without systematically comparing alternative representation strategies. To address this gap, we present the first systematic empirical study on various feature extraction paradigms and integration strategies, along with hierarchical representations from frozen LVLMs for MVR. Extensive experiments on representative LVLMs reveal that hidden states from multiple decoder layers provide richer and more effective representations for MVR. Guided by this insight, we propose the Dual Feature Fusion (DFF) Framework, a lightweight approach that adaptively fuses multi-layer representations from frozen LVLMs with ID embeddings. DFF achieves state-of-the-art performance on two real-world micro-video recommendation benchmarks, consistently outperforming strong baselines and providing a principled approach to integrating off-the-shelf large vision-language models into micro-video recommender systems.

Existing multimodal document question-answering (QA) systems predominantly rely on flat semantic retrieval, representing documents as a set of disconnected text chunks and largely neglecting their intrinsic hierarchical and relational structures. Such flattening disrupts logical and spatial dependencies—such as section organization, figure-text correspondence, and cross-reference relations—that humans naturally exploit for comprehension. To address this limitation, we introduce a document-level structural Document MAP (DMAP), which explicitly encodes both hierarchical organization and inter-element relationships within multimodal documents. Specifically, we design a Structured-Semantic Understanding Agent to construct DMAP by organizing textual content together with figures, tables, charts, etc into a human-aligned hierarchical schema that captures both semantic and layout dependencies. Building upon this representation, a Reflective Reasoning Agent performs structure-aware and evidence-driven reasoning, dynamically assessing the sufficiency of retrieved context and iteratively refining answers through targeted interactions with DMAP. Extensive experiments on MMDocQA benchmarks demonstrate that DMAP yields document-specific structural representations aligned with human interpretive patterns, substantially enhancing retrieval precision, reasoning consistency, and multimodal comprehension over conventional RAG-based approaches. Code is available at https://github.com/Forlorin/DMAP

Recommender system (RS) aims to capture personalized preferences from massive user behaviors, making them pivotal in the era of information explosion. However, the presence of “information cocoons,” interaction sparsity, cold-start problem, and feedback loops inherent in RS make users interact with a limited number of items. Conventional recommendation algorithms typically focus on the positive historical behaviors, while neglecting the essential role of negative feedback in user preference understanding. As a promising but easy-to-ignored area, negative sampling is proficient in revealing the genuine negative aspect inherent in user behaviors, emerging as an inescapable procedure in RS. In this survey, we first discuss existing user feedback, the critical role of negative sampling and the optimization objectives in RS, and thoroughly analyze challenges that consistently impede its progress. Then, we conduct an extensive literature review on the existing negative sampling strategies in RS and classify them into five categories with their discrepant techniques. Finally, we detail the insights of the tailored negative sampling strategies in diverse RS scenarios and outline an overview of the prospective research directions toward which the community may engage and benefit.

Task-oriented conversational agents strive to aid users across various tasks by concentrating on generating suitable responses to guarantee successful task accomplishment. Nonetheless, several factors have a substantial influence on user contentment beyond task fulfillment, requiring further investigation. Within this work, we aim to analyze diverse behavioral patterns of conversational agents with the goal of enhancing user satisfaction. Our findings lead to the exploration of three different enriched response generation schemes: EnRG-ATT, EnRG-TIP, and EnRG-SIM. Specifically, EnRG-ATT is designed to integrate the model's capabilities with a dual attention mechanism across two distinct modalities of external resources. It employs a pair of gates to regulate the utilization of such sources efficiently. More elegantly, we introduce EnRG-TIP, which simplifies response enrichment as a sequence prediction problem and exploits the pre-trained language model to capture user tips related to the conversation. Moreover, building on the efficiency of grounding on similar responses, EnRG-SIM further enhances response generation by inserting similar responses into the training sequences, to direct the pre-trained model's attention towards this additional knowledge. Our comprehensive experiments demonstrate that our three proposed methods not only achieve good task completion but also generate responses that yield higher user satisfaction.

Bundle recommendation approaches offer users a set of related items on a particular topic. The current state-of-the-art (SOTA) method utilizes contrastive learning to learn representations at both the bundle and item levels. However, due to the inherent difference between the bundle-level and item-level preferences, the item-level representations may not receive sufficient information from the bundle affiliations to make accurate predictions. In this article, we propose a novel approach, Enhanced Bundle Recommendation (EBRec), which incorporates two enhanced modules to explore inherent item-level bundle representations. First, we propose to incorporate the bundle-user-item (B-U-I) high-order correlations to explore more collaborative information, thus to enhance the previous bundle representation that solely relies on the bundle-item affiliation information. Second, we further enhance the B-U-I correlations by augmenting the observed user-item interactions with interactions generated from pre-trained models, thus improving the item-level bundle representations. We conduct extensive experiments on three public datasets, and the results justify the effectiveness of our approach as well as the two core modules. Codes and datasets are available at https://github.com/answermycode/EBRec .

Bundle recommendation seeks to recommend a bundle of related items to users to improve both user experience and the profits of platform. Existing bundle recommendation models have progressed from capturing only user-bundle interactions to the modeling of multiple relations among users, bundles, and items. CrossCBR, in particular, incorporates cross-view contrastive learning into a two-view preference learning framework, significantly improving SOTA performance. It does, however, have two limitations: (1) the two-view formulation does not fully exploit all the heterogeneous relations among users, bundles, and items; and (2) the “early contrast and late fusion” framework is less effective in capturing user preference and difficult to generalize to multiple views. In this article, we present MultiCBR, a novel Multi -view C ontrastive learning framework for B undle R ecommendation. First, we devise a multi-view representation learning framework capable of capturing all the user-bundle, user-item, and bundle-item relations, especially better utilizing the bundle-item affiliations to enhance sparse bundles’ representations. Second, we innovatively adopt an “early fusion and late contrast” design that first fuses the multi-view representations before performing self-supervised contrastive learning. In comparison to existing approaches, our framework reverses the order of fusion and contrast, introducing the following advantages: (1) Our framework is capable of modeling both cross-view and ego-view preferences, allowing us to achieve enhanced user preference modeling; and (2) instead of requiring quadratic number of cross-view contrastive losses, we only require two self-supervised contrastive losses, resulting in minimal extra costs. Experimental results on three public datasets indicate that our method outperforms SOTA methods. The code and dataset can be found in the github repo https://github.com/HappyPointer/MultiCBR .

Current deep learning-based image manipulation localization methods achieve impressive performance when rich spatial features and information are fully utilized. However, most of them suffer from the irrelevance of semantic awareness when identifying various manipulation categories. This leads to false alarms on recognizing forged regions. In this paper, we propose a Progressively-Refined Neural Network (PR-Net), to localize the tampered regions progressively under a coarse-to-fine workflow. Specifically, PR-Net is composed of a Feature Extractor (FE) that captures feature intrinsic correlations and a Mask Generation Module (MGM) with three refining generators. The FE takes a CNN to extract the image features and introduces an attention mechanism Convolution Block Attention Module (CBAM) to suppress the image content and guide the extractor in exploring the inconsistencies between the manipulated and authentic regions. The MGM comprises three generators where the Coarse Mask RR-Generator generates a localization result roughly, the Candidate Mask RR-Generator generates a possible tampered region according to the rough localization measure, and the Fine Mask RR-Generator produces the final prediction of manipulated regions. We also utilize the Rotated Residual (RR) structure to suppress the image content during the generative process. The extensive experimental results on four benchmark data sets (NIST16, COVER, CASIA v1.0, and In-The-Wild) demonstrate the superior performance of PR-Net compared with the state-of-the-art methods in localizing the manipulated regions.

Deep learning has become an emerging technical for image manipulation localization, which can automatically recognize abnormal traces caused by manipulation. However, as manipulations mainly happens in the foreground regions, these methods largely focus on the foreground contents and neglect the background, which contain complementary signal for fully understanding the image and are meaningful for manipulation localization. We propose a Mutually-Complementary Network (MC-Net), which is a two-branch network to operate the foreground and background features, respectively. To distill complementary signals from the features, we propose a mutual attentive module composed of self-feature attentive, and cross-feature attentive components to advance the communication across the foreground and background branches. Extensive qualitative and quantitative experiments demonstrate that our proposed MC-Net distinctly improves the prediction of foreground and background, obtains consistent performance increments on four benchmark data sets, and significantly outperforms the state-of-the-art methods.

With the prevalence of multimedia content on the Web, developing recommender solutions that can effectively leverage the rich signal in multimedia data is in urgent need. Owing to the success of deep neural networks in representation learning, recent advances on multimedia recommendation has largely focused on exploring deep learning methods to improve the recommendation accuracy. To date, however, there has been little effort to investigate the robustness of multimedia representation and its impact on the performance of multimedia recommendation. In this paper, we shed light on the robustness of multimedia recommender system. Using the state-of-the-art recommendation framework and deep image features, we demonstrate that the overall system is not robust, such that a small (but purposeful) perturbation on the input image will severely decrease the recommendation accuracy. This implies the possible weakness of multimedia recommender system in predicting user preference, and more importantly, the potential of improvement by enhancing its robustness. To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning. The idea is to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model's accuracy. We conduct experiments on two representative multimedia recommendation tasks, namely, image recommendation and visually-aware product recommendation. Extensive results verify the positive effect of adversarial learning and demonstrate the effectiveness of our AMR method. Source codes are available in https://github.com/duxy-me/AMR.

Most existing image enhancement methods function like a black box, which cannot clearly reveal the procedure behind each image enhancement operation. To overcome this limitation, in this paper, we design a progressive image enhancement framework, which generates an expected "good" retouched image with a group of self-interpretable image filters under the guidance of an aesthetic assessment model. The introduced aesthetic network effectively alleviates the shortage of paired training samples by providing extra supervision, and eliminate the bias caused by human subjective preferences. The self-interpretable image filters designed in our image enhancement framework, make the overall image enhancing procedure easy-to-understand. Extensive experiments demonstrate the effectiveness of our proposed framework.

As the core of recommender systems, collaborative filtering (CF) models the affinity between a user and an item from historical user-item interactions, such as clicks, purchases, and so on. Benefiting from the strong representation power, neural networks have recently revolutionized the recommendation research, setting up a new standard for CF. However, existing neural recommender models do not explicitly consider the correlations among embedding dimensions, making them less effective in modeling the interaction function between users and items. In this work, we emphasize on modeling the correlations among embedding dimensions in neural networks to pursue higher effectiveness for CF. We propose a novel and general neural collaborative filtering framework—namely, ConvNCF, which is featured with two designs: (1) applying outer product on user embedding and item embedding to explicitly model the pairwise correlations between embedding dimensions, and (2) employing convolutional neural network above the outer product to learn the high-order correlations among embedding dimensions. To justify our proposal, we present three instantiations of ConvNCF by using different inputs to represent a user and conduct experiments on two real-world datasets. Extensive results verify the utility of modeling embedding dimension correlations with ConvNCF, which outperforms several competitive CF methods.

Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Ranking (BPR). Using matrix Factorization (MF) - the most widely used model in recommendation - as a demonstration, we show that optimizing it with BPR leads to a recommender model that is not robust. In particular, we find that the resultant model is highly vulnerable to adversarial perturbations on its model parameters, which implies the possibly large error in generalization. To enhance the robustness of a recommender model and thus improve its generalization performance, we propose a new optimization framework, namely Adversarial Personalized Ranking (APR). In short, our APR enhances the pairwise ranking method BPR by performing adversarial training. It can be interpreted as playing a minimax game, where the minimization of the BPR objective function meanwhile defends an adversary, which adds adversarial perturbations on model parameters to maximize the BPR objective function. To illustrate how it works, we implement APR on MF by adding adversarial perturbations on the embedding vectors of users and items. Extensive experiments on three public real-world datasets demonstrate the effectiveness of APR - by optimizing MF with APR, it outperforms BPR with a relative improvement of 11.2% on average and achieves state-of-the-art performance for item recommendation. Our implementation is available at: \urlhttps://github.com/hexiangnan/adversarial_personalized_ranking.