Live streaming platforms require real-time monitoring and reaction to social signals, utilizing partial and asynchronous evidence from video, text, and audio. We propose StreamSense, a streaming detector that couples a lightweight streaming encoder with selective routing to a Vision–Language Model (VLM) expert. StreamSense handles most timestamps with the lightweight streaming encoder, escalates hard/ambiguous cases to the VLM, and defers decisions when context is insufficient. The encoder is trained using (i) a cross-modal contrastive term to align visual/audio cues with textual signals, and (ii) an IoU-weighted loss that down-weights poorly overlapping target segments, mitigating label interference across segment boundaries. We evaluate StreamSense on multiple social streaming detection tasks (e.g., sentiment classification and hate content moderation), and the results show that StreamSense achieves higher accuracy than VLM-only streaming while only occasionally invoking the VLM, thereby reducing average latency and compute. Our results indicate that selective escalation and deferral are effective primitives for understanding streaming social tasks. Code is publicly available on GitHub.
论文检索
输入标题、作者或关键词，从 13,734 篇学术成果中精准定位
User behavior on social media---from scrolling and viewing to liking, reposting, and posting---yet most research relies on self-reports that obscure fine-grained usage patterns. We analyze high-resolution activity logs from 209 U.S. X (Twitter) users tracked over four weeks to identify distinct behavioral profiles based on session-level features. Latent profile analysis reveals three groups---interactors (32.52%), lurkers (60.45%), and creators (7.03%) that differ in engagement intensity, demographics, and content exposure. Interactors and lurkers skew younger and Democratic, whereas creators skew older and more Republican, consuming more ideological and low-credibility content. These results link behavioral heterogeneity to systematically different information environments and suggest that platform interventions may operate unevenly across user types. Our findings demonstrate the value of log-based behavioral segmentation for understanding online participation and motivate profile-aware platform governance and content moderation strategies.
Web searchers continuously form expectations about document content based on snippets and titles, yet when these expectations are violated, their attention and satisfaction are disrupted. Detecting such expectancy violations in real-time can enable adaptive, user-aware Web systems that respond to cognitive mismatches. This paper investigates whether eye-tracking features can predict expectancy violations during Web search and identifies which temporal aspects of attention carry predictive information. Using data from 34 participants performing controlled search tasks, we extracted four gaze metrics, i.e. time to first fixation, total fixation duration, number of fixations, and mean fixation duration, and trained machine learning models using a leave-one-participant-out cross-validation approach. Sustained attention features, particularly total fixation duration and number of fixations, predicted expectancy violations with 62.6% accuracy (p = .008), while initial attention metrics performed at chance. The results reveal that expectancy violations manifest through extended visual engagement rather than immediate orienting responses. The findings of this work contribute to the theoretical understanding of user–system interaction on the Web and provide a foundation for adaptive retrieval interfaces capable of detecting cognitive surprise and delivering timely support.
Topic modeling plays a critical role in organizing and understanding large-scale web content. While neural topic models (NTMs) based on variational autoencoders (VAEs) have achieved notable success in analyzing textual data, they remain limited in addressing the multimodal nature of modern web content. Existing unimodal or multimodal extensions often suffer from posterior collapse and fail to capture the directional semantics inherent in both text and images, resulting in incoherent topics and limited interpretability. To address these challenges, we propose MM-vNTM (MultiModal Neural Topic Model with von Mises-Fisher Mixtures), a framework for web-scale topic discovery over multimodal data. MM-vNTM leverages pre-aligned cross-modal embeddings as inputs and jointly models document-level representations of text and image modalities in a shared hyperspherical latent space. Furthermore, it defines topics as mixtures of von Mises-Fisher (vMF) distributions in the L2-normalized word embedding space, explicitly capturing directional similarity. Experiments on multimedia web datasets demonstrate that MM-vNTM consistently outperforms state-of-the-art unimodal and multimodal baselines in terms of overall topic quality, highlighting its effectiveness for real-world web scenarios.
Trending news detection in low-traffic search environments faces a fundamental cold-start problem, where a lack of query volume prevents systems from identifying emerging or long-tail trends. Existing methods relying on keyword frequency or query spikes are inherently slow and ineffective in these sparse settings, lagging behind real-world shifts in attention. We introduce RTTP, a novel Real-Time Trending Prediction framework that generates search queries directly from news content instead of waiting for users to issue them. RTTP leverages a continual learning LLM (CL-LLM) that converts posts into search-style queries and scores them using engagement strength + creator authority, enabling early trend surfacing before search volume forms. To ensure adaptation without degrading reasoning, we propose Mix-Policy DPO, a new preference-based continual learning approach that combines on-policy stability with off-policy novelty to mitigate catastrophic forgetting during model upgrades. Deployed at production scale on Facebook and Meta AI products, RTTP delivers +91.4% improvement in tail-trend detection precision@500 and +19% query generation accuracy over industry baselines, while sustaining stable performance after multi-week online training. This work demonstrates that LLM-generated synthetic search signals, when aligned and continually updated, unlock timely trend understanding in low-traffic search environments.
User interactions on e-commerce platforms are inherently diverse, involving behaviors such as clicking, favoriting, adding to cart, and purchasing. The transitions between these behaviors offer valuable insights into user-item interactions, serving as a key signal for understanding evolving preferences. Consequently, there is growing interest in leveraging multi-behavior data to better capture user intent. Recent studies have explored sequential modeling of multi-behavior data, many relying on transformer-based architectures with polynomial time complexity. While effective, these approaches often incur high computational costs, limiting their applicability in large-scale industrial systems with long user sequences. To address this challenge, we propose the Transition-Aware Graph Attention Network (TGA), a linear-complexity approach for modeling multi-behavior transitions. Unlike traditional transformers that treat all behavior pairs equally, TGA constructs a structured sparse graph by identifying informative transitions from three perspectives: (a) item-level transitions, (b) category-level transitions, and (c) neighbor-level transitions. Built upon the structured graph, TGA employs a transition-aware graph Attention mechanism that jointly models user-item interactions and behavior transition types, enabling more accurate capture of sequential patterns while maintaining computational efficiency. Experiments show that TGA outperforms all state-of-the-art models while significantly reducing computational cost. Notably, TGA has been deployed in a large-scale industrial production environment, where it leads to impressive improvements in key business metrics.
Money laundering enables malicious actors to integrate illegal profits into the legitimate economy and has long been a central concern in financial regulation. Blockchain systems introduce new channels for laundering through decentralized, pseudonymous, and cross-border asset transfers. In this context, blockchain exploiters often rely on laundering to conceal fund origins and enable cash-out. While prior work has focused on detecting suspicious accounts or transactions, the behavioral patterns underlying laundering practices remain underexplored. This paper provides a behavioral perspective on post-exploit laundering on Ethereum. We use on-chain tracing to reconstruct token flows originating from exploiter-controlled addresses. We then define a set of behavioral metrics covering financial trajectories, temporal dynamics, structural topology, and value dispersion. Our empirical study reveals recurring patterns, including rapid fund movement, shallow transfer structures, and broad dispersion. These patterns exhibit measurable regularities, suggesting that behavioral dynamics could be leveraged to enhance existing laundering detection frameworks.
Community detection (CD) on signed networks is crucial for understanding how positive and negative relations jointly shape network structure. However, existing CD methods often yield inconsistent communities due to noisy or conflicting edge signs. In this paper, we propose ReCon, a model-agnostic post-processing framework that progressively refines community structures through four iterative steps: (1) structural refinement, (2) boundary refinement, (3) contrastive learning, and (4) clustering. Extensive experiments on eighteen synthetic and four real-world networks using four CD methods demonstrate that ReCon consistently enhances community detection accuracy, serving as an effective and easily integrable solution for reliable CD across diverse network properties.
Multilingual Text-Centric Visual Question Answering (TEC-VQA) has become crucial for real-world applications, as it requires fine-grained understanding and reasoning over multilingual scene text. Recent advances in vision-language models (VLMs) have demonstrated strong potential in tackling multimodal tasks. However, most existing approaches rely primarily on textual Chain-of-Thought (CoT) and provide limited support for multilingual multimodal reasoning. To address this gap, we introduce LaV-CoT, the first Language-aware Visual CoT framework with Multi-Aspect Reward Optimization. LaV-CoT incorporates an interpretable multi-stage reasoning pipeline consisting of text summary with bounding box, language identification, spatial object-level captioning, and step-by-step logical reasoning. To improve reasoning accuracy and cross-lingual generalization, we propose a novel verifiable Multi-Aspect Reward Optimization in addition to supervised fine-tuning that incorporates rewards for linguistic consistency, structural fidelity, and response accuracy. Extensive evaluations on public datasets, including MMMB, Multilingual MMBench, and MTVQA, show that LaV-CoT outperforms open-source models of similar size by up to ~9.5% accuracy, even surpassing open-source models more than twice its size, and further exceeding several state-of-the-art proprietary models. Moreover, LaV-CoT has been integrated into our online Intelligent Document Processing platform. A further online A/B test demonstrates an \(\sim\)8.7% improvement in acceptance rate, validating its effectiveness in industrial deployment and commercial applications. Our code is available at this https://github.com/HJNVR/LaV-CoT repository.
Autonomous Feature Engineering (AFE) is critical for improving predictive performance on tabular data by relieving humans from manual feature crafting. However, traditional AFE lacks the semantic guidance needed to fully exploit domain knowledge. Although large language models (LLMs) can, in principle, emulate experts, existing approaches typically operate in an open code space that directly generates and rewrites entire features; without a compositional structural representation and invariant constraints, edits are coarse and non-local, making it hard to distill interpretable features with high information content and rich hierarchical structure. We propose AFE-Master, a novel LLM-driven AFE framework that shifts feature construction from black-box evolution to structural and semantically rigorous search. AFE-Master uses a domain-specific language (DSL) to explicitly represent feature transformations and parses them into abstract syntax trees (ASTs), enabling the LLM to understand and manipulate feature structures with clear semantics. On this interpretable representation, we employ guided local search (GLS) over syntactic and semantic neighborhoods, making small, checkable edits that efficiently and controllably discover information-dense, hierarchically structured features. Experiments spanning Kaggle and OpenML benchmarks as well as multiple tabular models (XGBoost, MLP, and the frontier TabPFN) show significant gains. At industrial scale, we further conduct a large online A/B test on the advertising recommendation service of a major mobile app store. Starting from a mature, large feature set—167 expert-crafted features refined over two years—we add 20 features automatically generated by AFE-Master. On 100M+ live samples, a well-engineered FiBiNET model achieves +15.11% CPM and +3.01% CTR, demonstrating practical value and transferability under both massive sample volume and a high-feature-count production setting. These results indicate that AFE-Master's semantically guided approach can discover expert-level features beyond the reach of prior methods, pointing to a new generation of interpretable, high-performance AFE techniques.
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With the breakthroughs in large language models (LLMs), mainstream embedding models have gradually shifted from BERT to LLMs for more accurate text modeling. However, these models still adopt direct-embedding methods, and the semantic accuracy of embeddings remains inadequate. Therefore, contrastive learning is heavily employed to achieve tight semantic alignment between positive pairs. Consequently, such models tend to capture statistical co-occurrence patterns in the training data, biasing them toward shallow lexical and semantic matches. For difficult queries exhibiting notable lexical disparity from target items, the performance degrades significantly. In this work, we propose the Large Reasoning Embedding Model (LREM), which novelly integrates reasoning processes into representation learning. For difficult queries, LREM first conducts reasoning to achieve a deep understanding of the original query, and then produces a reasoning-augmented query embedding for retrieval. This reasoning process effectively bridges the semantic gap between original queries and target items, significantly improving retrieval accuracy. Specifically, we adopt a two-stage training process: the first stage optimizes the LLM on carefully curated Query-CoT-Item triplets with SFT and InfoNCE losses to establish preliminary reasoning and embedding capabilities, and the second stage further refines the reasoning trajectories via reinforcement learning (RL). Extensive offline and online experiments validate the effectiveness of LREM, leading to its deployment on China's largest e-commerce platform since August 2025.
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and exert an indirect, yet substantial impact on business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reasoning capacity for long-tail and challenging cases. Efforts to address this via reinforcement learning strategies like Group Relative Policy Optimization (GRPO) often suffer from sparse terminal rewards, offering insufficient guidance for multi-step reasoning, which in turn slows convergence. To address these challenges, we propose TaoSR-AGRL, an Adaptive Guided Reinforcement Learning framework for LLM-based relevance prediction in Taobao Search Relevance. TaoSR-AGRL introduces two key innovations: (1) Rule-aware Reward Shaping, which decomposes the final relevance judgment into dense, structured rewards aligned with domain-specific relevance criteria; and (2) Adaptive Guided Replay, which identifies low-accuracy rollouts during training and injects targeted ground-truth guidance to steer the policy away from stagnant, rule-violating reasoning patterns toward compliant trajectories. TaoSR-AGRL was evaluated on large-scale datasets and through online evaluations on Taobao Search. It consistently outperforms DPO and GRPO baselines, improving relevance accuracy and rule adherence, with measurable gains in user engagement and stable training dynamics. The model has been deployed on Taobao, serving hundreds of millions of users.
Web recommendations provide personalized items from massive catalogs for users, which rely heavily on retrieval stages to trade off the effectiveness and efficiency of selecting a small relevant set from billion-scale candidates in online digital platforms. As one of the largest Chinese search engine and news feed providers, Baidu resorts to Deep Neural Network (DNN) and graph-based Approximate Nearest Neighbor Search (ANNS) algorithms for accurate relevance estimation and efficient search for relevant items. However, current retrieval at Baidu fails in comprehensive user-item relational understanding due to dissected interaction modeling, and performs inefficiently in large-scale graph-based ANNS because of suboptimal traversal navigation and the GPU computational bottleneck under high concurrency. To this end, we propose a GPU-accelerated Multi-relational Parallel Graph Retrieval (GMP-GR) framework to achieve effective yet efficient retrieval in web-scale recommendations. First, we propose a multi-relational user-item relevance metric learning method that unifies diverse user behaviors through multi-objective optimization and employs a self-covariant loss to enhance pathfinding performance. Second, we develop a hierarchical parallel graph-based ANNS to boost graph retrieval throughput, which conducts breadth-depth-balanced searches on a large-scale item graph and cost-effectively handles irregular neural computation via adaptive aggregation on GPUs. In addition, we integrate system optimization strategies in the deployment of GMP-GR in Baidu. Extensive experiments demonstrate the superiority of GMP-GR in retrieval accuracy and efficiency. Deployed across more than twenty applications at Baidu, GMP-GR serves hundreds of millions of users with a throughput exceeding one hundred million requests per second.
In the rapidly evolving landscape of e-commerce, visual search has become a cornerstone of user experience, enabling customers to find products using images rather than traditional text queries. However, a comprehensive analysis reveals a persistent challenge: nearly half of retrieval failures stem from systems that prioritize superficial visual similarity over semantic relevance, resulting in frustrating user experiences where searches return visually similar but functionally different products. This limitation becomes particularly acute in Business-to-Business environments, where incorrect product recommendations can have significant operational and safety implications. In this paper, we propose a novel solution, Adaptive Retrieval with Category-aware Hierarchical sEmantic Refinement (ARCHER), which presents a novel multimodal retrieval framework that addresses these challenges through progressive semantic alignment. Unlike existing approaches that treat all visual similarities equally, ARCHER employs a sophisticated three-stage learning strategy that systematically builds from coarse-grained category understanding to fine-grained product discrimination. The framework begins with Proto-Align Enhancement to establish foundational visual-textual correspondences, progresses through Cross-View Learning to develop robust viewpoint-invariant representations, and culminates with Margin-based Representation Enhancement that learns to distinguish between visually similar but functionally distinct products. Most significantly, the framework has been successfully deployed on Alibaba.com's B2B platform since December 2024, where it serves millions of daily queries and has achieved a measurable 2.1% improvement in click-through rates.
Understanding how media rhetoric shapes audience engagement is crucial in the attention economy. This study examines how moral-emotional framing by mainstream news channels on YouTube influences user behavior across Korea and the United States. To capture the platform's multimodal nature, combining thumbnail images and video titles, we develop a multimodal moral emotion classifier by fine-tuning a vision–language model. The model is trained on human-annotated multimodal datasets in both languages and applied to approximately 400,000 videos from major news outlets. We analyze three engagement levels (views, likes, and comments), representing increasing degrees of commitment. The results show that other-condemning rhetoric—expressions of moral outrage that criticize others' morality—consistently increases all forms of engagement across cultures, with effect sizes strengthening from passive viewing to active commenting. These findings suggest that moral outrage is a particularly effective emotional strategy, attracting not only attention but also active participation. We discuss concerns about the potential misuse of other-condemning rhetoric, as such practices may deepen polarization by reinforcing in-group/out-group divisions. To facilitate future research and ensure reproducibility, we publicly release our Korean and English multimodal moral emotion classifiers.
The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that involve multimodal manipulation, AI-generated content, cognitive bias, and out-of-context reuse. Meanwhile, most detection models lack fine-grained attribution, limiting interpretability and practical utility. To address these gaps, we introduce WildFakeBench, a large-scale benchmark of over 10,000 real-world micro-videos covering diverse misinformation types and sources, each annotated with expert-defined attribution labels. Building on this foundation, we develop FakeAgent, a Delphi-inspired multi-agent reasoning framework that integrates multimodal understanding with external evidence for attribution-grounded analysis. FakeAgent jointly analyzes content and retrieved evidence to identify manipulation, recognize cognitive and AI-generated patterns, and detect out-of-context misinformation. Extensive experiments show that FakeAgent consistently outperforms existing MLLMs across all misinformation types, while WildFakeBench provides a realistic and challenging testbed for advancing explainable micro-video misinformation detection.. Data and code are available at: https://github.com/Aiyistan/FakeAgent.
Multimodal Sentiment Analysis (MSA) and Emotion Recognition in Conversations (ERC) have rapidly developed into pivotal tasks in artificial intelligence. Large Language Models (LLMs) offer powerful semantic reasoning and computational capabilities, showing great potential for understanding emotional content. However, when applied to multimodal sentiment data, LLMs face significant challenges, including the inability to directly process heterogeneous data, difficulties in coping with feature misalignment and suboptimal cross-modal fusion. To address these challenges, we propose a novel multimodal sentiment inference framework named ATGFB-MFF which grounded in fiber bundle theory. This method decomposes multimodal features into an adaptive text-guided shared semantic space and fiber offset spaces to achieve structured alignment and fusion. Then the fused features are converted into structured pseudo-token sequences for effective inference via frozen LLMs. We also introduce two loss functions respectively called shared space consistency loss and fiber offset regularization loss which are used to improve representation stability. Extensive experiments on four benchmark datasets demonstrate that ATGFB-MFF consistently outperforms state-of-the-art baselines. These results highlight the efficacy of geometric structural modeling in unlocking the potential of LLMs for multimodal sentiment inference.
Knowledge Tracing (KT) is a core task in intelligent tutoring systems, designed to model the dynamic evolution of students' knowledge states by predicting their performance on specific problems. However, existing KT models, primarily developed for traditional subject domains, exhibit poor generalization to programming tasks due to several distinct challenges. First, student responses in programming tasks are characterized by high uncertainty. Second, programming tasks typically provide continuous scores based on the proportion of passed test cases, in contrast to the binary correctness assumed by traditional KT models, with these test-case-based scores often being noisy. Third, most KT models rely exclusively on the understanding of knowledge concepts for performance prediction, whereas success in programming tasks is heavily contingent upon logical reasoning and problem-specific comprehension. To address these issues, we propose an LLM-driven Interaction Enrichment Framework (MIE) to mitigate high uncertainty and problematic labeling, and introduce the Multi-Level Programming Knowledge Tracing (MLPKT) model to capture students' knowledge states across multiple dimensions. MLPKT conducts multi-layer analysis of student submissions to identify the root causes of errors and assign semantically meaningful fine-grained labels. Additionally, we propose a three-level, three-phase KT architecture that captures knowledge dynamics across three dimensions—problems, concepts, and logical skills—through the phases of learning, forgetting/reinforcement, and application. Extensive experiments on three datasets demonstrate that MIE+MLPKT consistently outperforms 18 baseline methods. Our code is available at: https://anonymous.4open.science/r/MIE-MLPKT-D654.
Low-rank adaptation (LoRA) has emerged as an efficient fine-tuning technique for large language models, enabling parameter-efficient updates while maintaining task performance. However, LoRA suffers from two key issues: 1) inefficient feature learning when the width n (embedding dimension) is large, and 2) ineffective updates to the adapter matrix A due to the initialization of B as zero. We propose LoRA-E2, which utilizes a Gaussian initialization with variance Θ(n-3/4 ) for A, and employs the Gauss-Seidel iteration to train B and A. We theoretically show that LoRA-E2 enables more stable and efficient feature learning with effective parameter updates over standard LoRA. Empirically, LoRA-E2 achieves consistent gains in both natural language understanding and generation tasks. On the GLUE benchmark with T5-base, it improves performance by 1–10% over LoRA. When fine-tuning LLaMA 2-7B on MetaMathQA with GSM8K as validation, LoRA-E2 surpasses LoRA by 1–2% and converges up to ∼3× faster. Code is available at https://github.com/whu-totemdb/LoRA-E2.
The prevalence of sarcasm in multimodal dialogues on the social platforms presents a crucial yet challenging task for understanding the true intent behind online content. Comprehensive sarcasm analysis requires two key aspects: Multimodal Sarcasm Detection (MSD) and Multimodal Sarcasm Explanation (MuSE). Intuitively, the act of detection is the result of the reasoning process that explains the sarcasm. Current research predominantly focuses on addressing either MSD or MuSE as a single task. Even though some recent work has attempted to integrate these tasks, their inherent causal dependency is often overlooked. To bridge this gap, we propose MuVaC, a variational causal inference framework that mimics human cognitive mechanisms for understanding sarcasm, enabling robust multimodal feature learning to jointly optimize MSD and MuSE. Specifically, we first model MSD and MuSE from the perspective of structural causal models, establishing variational causal pathways to define the objectives for joint optimization. Next, we design an alignment-then-fusion approach to integrate multimodal features, providing robust fusion representations for sarcasm detection and explanation generation. Finally, we enhance the reasoning trustworthiness by ensuring consistency between detection results and explanations. Experimental results demonstrate the superiority of MuVaC in public datasets, offering a new perspective for understanding multimodal sarcasm.