Personalized sequential recommendation aims to predict the appropriate items to users from their behavioral sequences. To alleviate the data sparsity and interest drift issues, conventional approaches typically utilize the additional behaviors from other domains via cross-domain transition. However, existing cross-domain sequential recommendation (CDSR) algorithms follow the align-then-fusion paradigm which conducts the representation-level alignment across multiple domains and mechanically combine them for recommendation, overlooking the fine-grained multi-domain fusion. Inspired by the advancements of diffusion models (DMs) in distribution matching, we propose an align-for-fusion framework for CDSR to Harmonize triple preferences utilizing Dual-oriented DMs (HorizonRec). Specifically, we first investigate the uncertainty injection of DMs and attribute the fundamental factor of the instability in existing DMs recommenders to the stochastic noise and propose a Mixed-conditioned Distribution Retrieval strategy which leverages the retrieved distribution from users' authentic behavioral logic as a bridge across the triple domains, enabling consistent multi-domain preference modeling. To suppress the potential noise and emphasize target-relevant interests during multi-domain user representation fusion, we further propose a Dual-oriented Preference Diffusion method to guide the extraction of preferences aligned with users' authentic interests from each domain under the supervision of the mixed representation. We conduct extensive experiments and analyses on four CDSR datasets from two distinct platforms to verify the effectiveness and robustness of our HorizonRec and its effective mechanism in fine-grained fusion of triple domains. Our code and datasets are available in https://github.com/YongfuZha/HorizonRec.

Visual-textual cross-modal hashing is an efficient method for large-scale multi-source heterogeneous data retrieval. However, existing unsupervised methods predominantly learn coarse-grained representations and establish global matching relationships, neglecting fine-grained alignment. Furthermore, image-text pairs exhibit partial semantic gaps and noise, leading to inaccurate similarity measurements. To tackle these issues, this paper proposes a Global-Regional Dual Hashing (GRDH) for unsupervised visual-textual retrieval, aiming to bridge the semantic ambiguity between image-text pairs and align multi-granularity representations within a unified transformer-based framework through concept similarity guidance. Specifically, we design the visual-textual transformers to extract global-region tokens from multimodal data. The region token refinement module is designed to eliminate semantically ambiguous region tokens, effectively reducing computational overhead for global-region interactions while promoting attention-based region information coordination. Secondly, under the guidance of concept-enhanced similarity, we constructed the global-regional semantic alignment loss that enables token-level and hash-level alignment in both continuous Euclidean space and discrete Hamming space. Finally, the global-regional dual hashing module generates hash codes of global-regional branches. Through cross-modal consistent hashing learning, it maintains semantic distribution consistency of cross-modal hash codes. Extensive experiments conducted on two baseline datasets (i.e., MIRFLICKR-25K and NUS-WIDE) demonstrate that our GRDH model outperforms recent state-of-the-art unsupervised methods, validating the effectiveness of our approach.

Multimodal Entity Linking (MEL) aims to disambiguate mentions in multimodal contexts by grounding them to specific entities in a knowledge base. A pivotal challenge in MEL is capturing multi-level correspondences: the semantic consistency between mention-entity pairs and the complementary correlations across modalities. However, existing methods often suffer from element dominance due to their reliance on coupled interactions or coarse global aggregations. In response, we propose the Multi-Element Collaborative Interaction (MECI) framework. First, to capture multi-element mention-entity correspondences, we develop a Multi-view Experts Network that leverages a ''divide-and-conquer'' strategy for decoupled feature learning to mitigate element dominance, supported by a KL-guided routing mechanism that governs expert specialization and collaboration. Furthermore, to model cross-modal complementary correlations, we propose a Hierarchical Multimodal Interaction Module, where a dynamic modality-aware weighting network refines interactions across hierarchical semantic levels, thereby integrating multi-granular evidence to counteract element dominance. Finally, we incorporate a generative semantic refinement stage that utilizes large language models for zero-shot re-ranking. Extensive experiments on WikiDiverse, RichpediaMEL, and WikiMEL show that MECI consistently outperforms state-of-the-art baselines, improving Hits@1 by 1.95%, 7.30%, and 2.31%, respectively.

Deepfake technology induces substantial societal challenges, establishing deepfake detection as an important area of research. However, existing research mainly relies on target deepfake datasets, which limits its generalizability across out-of-distribution tasks to some extent. Also, it often emphasizes visual modalities while neglecting the complementary information of the auditory data. Their autoregressive-based strategies also introduce long-term information interference, further constraining the detection performance. Consequently, the potential to exploit complementary relations between visual and auditory modalities and to leverage strongly correlated short-range information remains underexplored for the detection task. To address these challenges, this paper introduces Self-BiSterm, a novel self-supervised learning framework for deepfake detection. First, we propose a bidirectional synchronization distribution modeling mechanism, which calculates inconsistent distributions for video-to-audio and audio-to-video scenarios. This mechanism effectively measures audio-visual inconsistencies, improving the model's generalization performance in practical applications. Second, to mitigate the issue of long-term information distortion, we develop a short-term temporal dependency module to estimate the adjacent local receptive fields. This module facilitates the estimation of subsequent distributions by capturing short-term temporal dependencies with high precision. The effectiveness of the proposed Self-BiSterm framework is validated on various benchmarks, demonstrating superior performance compared to existing methods.

The cold-start problem, faced when providing recommendations to newly joined users with no historical interaction record existing in the platform, is one of the most critical problems that negatively impact the performance of a recommendation system. Fortunately, cross-domain recommendation~(CDR) is a promising approach for solving this problem, which can exploit the knowledge of these users from source domains to provide recommendations in the target domain. However, this method requires that the central server has the interaction behaviour data in both domains of all the users, which prevents users from participating due to privacy issues.