Timely nowcasting is critical for public safety during fast-evolving storms, where even short delays can trigger cascading failures—as in the October 2024 Spain flash flood that claimed over 90 lives within minutes. While radar offers reliable real-time sensing of atmospheric structure, models that collapse 3D volumes into 2D slices inevitably discard vertical information essential for capturing storm growth, phase transitions, and collapse. We introduce StormMind, a physically grounded framework that forecasts convective evolution by modeling causal interactions across stratified atmospheric layers. StormMind addresses two fundamental challenges:(1) the nonlinear, asynchronous coupling between low-, mid-, and high-level processes; and (2) reflectivity uncertainty, where storms with distinct vertical structures may appear deceptively similar on radar, masking their true phase and intensity. To tackle these issues, StormMind designs: i) a Convection Dynamics Extractor that models storm evolution from two complementary perspectives—horizontal morphology, capturing the spatial organization of physical processes within individual atmospheric layers, and vertical coupling, modeling energy exchanges across layers; and ii) a Convection Manifestation Reconstructor that adaptively fuses intra- and inter-layer signals, conditioned on the evolving storm state, to infer phase transitions (e.g., initiation, intensification, dissipation). Evaluated on the large-scale 3D-NEXRAD dataset (2020–2022, U.S.), StormMind outperforms strong baselines, achieving a 14.71% gain in CSI40. In real-world deployment with the Guangzhou Meteorological Bureau (Mar–May 2025), it improves CSI40 by 9.39% and boosts early-warning accuracy (98.33%)

With the rise of virtual communication and smart devices, speech has become the most natural medium of interaction. Yet it remains intrinsically difficult: speech is fleeting, unstructured, and disfluent, making key information prone to loss. Conventional Speech-to-Text (STT) systems attempt to acoustically reconstruct what was said. However, their frame-level alignment and rigid token-by-token decoding break down under noise, interruptions, or fragmentation. Humans, in contrast, readily grasp what was meant by exploiting syntax, discourse, pragmatics, and prosody. We argue for a paradigm shift from acoustic reconstruction to semantic transduction: inferring meaning directly from speech, abstracted from surface distortions. This shift raises two challenges: (C1) the lack of anchors between audio and meaning, and (C2) the need to maintain compositional semantics. To address these, we introduce CogTrans, a cognitively inspired speech-to-meaning framework. CogTrans tackles C1 through a Semantic Anchor Explorer, built on I-JEPA to capture higher-order regularities, prosodic rhythms, cross-frequency coarticulation, discourse continuity-providing resilient semantic scaffolds under noise and fragmentation. For C2, it designs a Lexical-Semantic Harmonizer that dynamically integrates these anchors with lexical embeddings; thereby preserving fine-grained compositional fidelity in roles, order, and entities. Extensive experiments show that CogTrans delivers consistent and substantial gains under challenging conditions. On GigaSpeech, it achieves a 6.58% relative Word Error Rate (WER) reduction, and on the multilingual VoxPopuli benchmark, the gain climbs to 12.97% at 10 dB noise-a regime where conventional models typically collapse. Beyond literal accuracy, CogTrans also boosts semantic fidelity, with a 3.40% increase in ROUGE-L and 3.45% in USE-Sim, ensuring transcripts remain faithful not only in words but also in meaning. Together, these results underscore that CogTrans is robust in noisy, unconstrained environments-precisely the conditions where reliability matters most.

Text-to-Vis is an emerging task in the data engineering and mining area that aims to automatically generate data visualizations from natural language questions (NLQs). Despite their progress, existing text-to-vis models often heavily rely on lexical matching between words in the questions and tokens in data schemas. This overreliance on lexical matching may lead to a diminished level of model robustness against input variations. In this study, we thoroughly examine the robustness of current text-to-vis models, an area that has not previously been explored. In particular, we construct the first robustness dataset nvBench-Rob, which contains diverse lexical and phrasal variations based on the original text-to-vis benchmark nvBench. Then, we found that the performance of existing text-to-vis models on this new dataset dramatically drops, implying that these methods exhibit inadequate robustness overall. Finally, we propose a novel framework based on Retrieval-Augmented Generation (RAG) technique, named GRED, specifically designed to address input perturbations in these two variants. The framework consists of three parts: NLQ-Retrieval Generator, Visualization Query-Retrieval Retuner and Annotation-based Debugger, which are used to tackle the challenges posed by natural language variants, programming style differences and data schema variants, respectively. Extensive experimental evaluations show that, compared to the state-of-the-art model Prompt4Vis in the Text-to-Vis field, GRED performs better in terms of model robustness, with a 40% increase in accuracy on the proposed nvBench-Rob dataset.

In recent years, an increasing number of deep reinforcement learning methods have achieved success in domains such as gaming, yet their inherent black-box nature poses significant challenges to the interpretability of the training process. Moreover, there is an urgent need for the ability to intervene directly and simply during training. To address these issues, we present the Interactive Hierarchical Reinforcement Learning Monitoring System (HRLMS). This framework integrates a set of rules derived from both autonomously generated rules and those input through user interaction, showcasing these rules in real-time during the training process. Throughout the system's operation, the input, integration, display, and reuse of rules form a comprehensive chain, enhancing the entirety of the workflow by seamlessly blending the training and display processes.

An emerging type of fraud involves malicious senders exploiting the blind shipment and cash-on-delivery (COD) mechanisms by dispatching large volumes of unsolicited, low-cost parcels. If unsuspecting receivers accept these parcels, they pay for both shipping and goods; otherwise, logistics providers bear the round-trip shipping costs. Existing detection techniques, which rely on extensive labeled cases, struggle with this emerging fraud because receivers' unawareness and low transaction values discourage complaints, resulting in few confirmed cases. Therefore, we propose leveraging receivers' complaints, though not initially collected for fraud detection, to uncover subtle indicators of fraud patterns, while addressing three challenges: (C1) noise-rich dialogues(C2) data privacy concerns, and (C3) ever-evolving fraud patterns. To address them, we design BLOFF, a Blind shipment detection Framework for LO gistics Fraud powered by large language models (LLMs). Specifically, BLOFF includes three components: i) Sensitivity Anonymization to protect sensitive user information; ii) Dialogue Profile Distillation to transform informal dialogues into structured representation, addressing C1, and distill knowledge from a teacher LLM (GPT-4o) to a lightweight student LLM (ChatGLM4-9B), addressing C2; ii) Multi-faceted Context Augmentation to enhance the interpretation of fraud signatures and adaptation of evolving patterns, addressing C3. We evaluate BLOFF on about 56,000 complaints records collected from JD Logistics between January and November 2024. Results show that BLOFF outperforms state-of-the-art methods, achieving a 10.19% improvement in precision. Furthermore, during its real-world deployment in December 2024, BLOFF identified over 90 fraudulent parcels with a 91.4% precision.

Map matching aims to align GPS trajectories to their actual travel routes on a road network, which is an essential pre-processing task for most of trajectory-based applications. Many map matching approaches utilize Hidden Markov Model (HMM) as their backbones. Typically, HMM treats GPS samples of a trajectory as observations and nearby road segments as hidden states. During map matching, HMM determines candidate states for each observation with a fixed searching range, and computes the most likely travel route using theViterbialgorithm. Although HMM-based approaches can derive high matching accuracy, they still suffer from high computation overheads. By inspecting the HMM process, we find that the computation bottleneck mainly comes from improper candidate sets, which contain many irrelevant candidates and incur unnecessary computations. In this paper, we present$\mathtt {LiMM}$– a learned road network index structure for efficient map matching.$\mathtt {LiMM}$improves existing HMM-based approaches from two aspects. First, we propose a novel learned index for road networks, which considers the characteristics of road data. Second, we devise an adaptive searching range mechanism to dynamically adjust the searching range for GPS samples based on their locations. As a result,$\mathtt {LiMM}$can provide refined candidate sets for GPS samples and thus accelerate the map matching process. Extensive experiments are conducted with three large real-world GPS trajectory datasets. The results demonstrate that$\mathtt {LiMM}$significantly reduces computation overheads by achieving an average speedup of$11.7\times$than baseline methods, merely with a subtle accuracy loss of 1.8%.

Dynamic ridesharing has garnered significant attention in recent years due to its numerous benefits. Existing ridesharing algorithms often employ a “filter-and-refine” frame-work, where a large set of candidate vehicles is initially selected for each ride order, followed by computationally intensive route planning for each candidate. However, this process can lead to significant response delays and limit system efficiency. To address this challenge, we propose an order-vehicle pre-matching recommendation approach (PreMR) that refines the candidate set before route planning. PreMR leverages spatial-temporal intervals and a self-attention mechanism to encode diverse order and vehicle information into uniform and informative representations, enabling it to accurately identify the most suitable vehicles for each order. Extensive experiments using real-world datasets and four representative ridesharing algorithms demonstrate that PreMR significantly reduces order response time (by 46.78% on average) while maintaining high service quality, with a slight trade-off in the order completion rate.

With the rapid and continuous development of data-driven technologies such as supervised learning, high-quality labeled data sets are commonly required by many applications. Due to the easiness of crowdsourcing small tasks with low cost, a straightforward solution for label quality improvement is to collect multiple labels from a crowd, and then aggregate the answers. The aggregation strategies include majority voting and its many variants, EM-based approaches, Graph Neural Nets and so on. However, due to the uncertainty information loss and commonly existing task correlations, the aggregated labels usually contain errors and may damnify the downstream model training.To address the above problem, we propose a hierarchical crowdsourcing framework1for data labeling with noisy answers about correlated data. We make use of the heterogeneity of the labeling crowd and form an initialization-checking-update loop to improve the quality of labeled data. We formalize and successfully solve the core optimization problem, namely, selecting a proper set of checking tasks for each round. We prove that maximizing the expected quality improvement is equivalent to minimizing the conditional entropy of the observations given the crowdsourced answer families for the selected task set, which is NP-hard to solve. Therefore, we design an efficient approximation algorithm and conduct a series of experiments on real data. The experimental results show that the proposed method effectively improves the quality of the labeled data sets as well as the SOTA performance, yet without extra human labor costs.

Personalizing the analysis for web search potentially improves the search experience. A good analytical model for web search should leverage not only collective wisdom but also individual characteristics. Most of the existing analytical models, however, focus on how to utilize the collective wisdom, from a crowd, for instance. In this paper, we address the problem of user-specific web search analysis by considering the so-called burstiness in web search, which captures the behavior of rare words appearing many times in a single document. We go beyond click graph and propose two probabilistic topic models, Topic Independence Model and Topic Dependence Model. The former adopts the assumption that the generation of query terms and URLs are topically independent, and the latter captures the coupling between search queries and URLs. We also capture the temporal burstiness of topics by utilizing continuous Beta distribution. Through a large-scale analysis of a real-life search query log, we observe that each user's web search trail enjoys multiple kinds of user-based unique characteristics. On a massive search query log, the new models achieve a better held-out likelihood than existing baselines, and they can also effectively reveal the latent evolution of topics on the corpus level and user-based level.

in this paper, we have made the first contribution by designing two right types of questions, namely Routing Query (RQ) to ask the crowd to decide the direction at each road intersection. Secondly, we propose a series of efficient algorithms to dynamically manage the questions in order to reduce the selection hardness within a limited budget. In particular, we show that there are two factors affecting the informativeness of a question: the randomness (entropy) of the question and the structural position of the road intersection. Furthermore, we extend the framework to enable multiple RQs per round. To ease the pain of the sample sensitiveness, we propose a new approach to reduce the selection hardness by reasoning on a so-called Selective Bayesian network. We compare our approach against several baselines, and the effectiveness and efficiency of our proposal are verified by the results in simulations and experiments on real-world datasets. The experimental results show that, even the Selective Bayesian Network provides only partial information of causality, the performance on the reduction of the selection hardness are dramatically improved, especially when the size of samples are relatively small.

Since inaccuracies commonly exist in many applications, data uncertainty has become an important problem in database systems. To deal with data uncertainty, probabilistic databases can be used to store uncertain data, and querying facilities are provided to yield answers with confidence. However, the results from a query or mining process may not be reliable when the uncertainty propagates in the systems. In this paper, we leverage the power of crowdsourcing by designing a set of Human Intelligence Tasks, or HITs in short, to ask a crowd to improve the quality of uncertain data. In particular, we consider crowds consists of workers with diverse accuracy rates when answering the HITs. We design solutions to maximize the data quality with minimal number of HITs. There are two obstacles for this non-trivial optimization, which lead to very high computational cost for selecting the optimal set of HITs. First, members of a crowd may return incorrect answers with different probabilities. Second, the HITs decomposed from uncertain data are often correlated. We have addressed these challenges in this paper by designing an effective approximation algorithm and an efficient heuristic solution, especially for crowds with diverse individual accuracy rates. To further improve the efficiency, we derive tight lower and upper bounds for effective filtering and estimation. Extensive experiments on both a simulated crowd and a real crowdsourcing platform are conducted to evaluate our solutions.

Taxi ridesharing becomes promising and attractive because of the wide availability of taxis in a city and tremendous benefits of ridesharing, e.g., alleviating traffic congestion and reducing energy consumption. Existing taxi ridesharing schemes, however, are not efficient and practical, due to they simply match ride requests and taxis based on partial trip information and omit the offline passengers, who hail a taxi at roadside with no explicit requests to the system. In this paper, we consider the mobility-aware taxi ridesharing problem, and present mT- Share to address these limitations. mT-Share fully exploits the mobility information of ride requests and taxis to achieve efficient indexing of taxis/requests and better passenger-taxi matching, while still satisfying the constraints on passengers' deadlines and taxis' capacities. Specifically, mT-Share indexes taxis and ride requests with both geographical information and travel directions, and supports the shortest path based routing and probabilistic routing to serve both online and offline ride requests. Extensive experiments with a large real-world taxi dataset demonstrate the efficiency and effectiveness of mT-Share, which can response each ride request in milliseconds and with a moderate detour cost. Compared to state-of-the-art methods, mT-Share serves 42% and 62% more ride requests in peak and non-peak hours, respectively.