The Material Point Method (MPM) provides a unified framework for simulating multi-material systems but struggles to allow for the separation of objects. Traditionally, multi-material simulations use a single background grid, which allows for automatic interaction between materials. Since particles of different types receive their velocities by interpolating from a common background grid, they are unable to efficiently separate. This is especially problematic when simulating immiscible fluids such as oil and water; once oil particles and water particles become mixed, they are unable to separate. A common solution is to solve different objects or materials on separate background grids, which allows particles of different materials to move with different velocities and separate. Using separate background grids loses the natural interaction between materials, since materials no longer interact through the background grid. In the case of immiscible fluids, phase separation is driven by thermodynamics and buoyancy. We present a novel method that enables natural buoyancy-driven phase separation in weakly compressible MPM. Our key observation is that compression and pressure do not depend on the type of particle. A local neighborhood of particles is compressed because particles are close together, and they exert pressure because they bump into the particles that are nearby. Correspondingly, we update the deformation gradient from a unified velocity field and use it to compute a unified pressure force. Combined with the use of separate background grids for velocity, this leads to a treatment of immiscible multiphase fluids that naturally separates due to buoyancy forces, even from a fully mixed configuration. We also propose a mixing potential that is capable of driving phase separation caused by thermodynamics even in the absence of gravity. Finally, we propose a novel algorithm for obtaining consistent per-phase level sets for rendering multiphase particle-based fluids.
论文检索
输入标题、作者或关键词，从 1,669 篇学术成果中精准定位
Accurate rainfall forecasting is essential for climate and disaster management, but precipitation exhibits extreme zero inflation that modern time-series Foundation Models (TSFMs) fundamentally cannot represent due to their continuous regression outputs. This structural mismatch causes pervasive drizzle-like false alarms, miscalibrated nonzero intensities, and severely underdetected extremes, while retraining large TSFMs is computationally prohibitive and environmentally unsustainable for most regions. We present a training-free wrapper that corrects zero inflation for frozen TSFMs without updating any parameters. Our method restores discrete zero mass using empirical occurrence statistics, aligns positive-value distributions via probability-integral transforms, and applies Generalized Pareto tail mapping for extreme-value consistency. Experiments on South Australian rainfall show substantial gains with negligible overhead (<5,ms per forecast, compared to hundreds of GPU-hours for retraining). The proposed wrapper enables carbon-neutral, globally deployable climate services and directly advances the goals of UN SDG~13 (Climate Action).
Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and forgery prevention for web content. Traditional noise-layer-based watermarking, however, remains vulnerable to inversion attacks that can recover embedded signals. To mitigate this, recent content-aware semantic watermarking schemes bind watermark signals to high-level image semantics, constraining local edits that would otherwise disrupt global coherence. Yet, large language models (LLMs) possess structured reasoning capabilities that enable targeted exploration of semantic spaces, allowing locally fine-grained but globally coherent semantic alterations that invalidate such bindings. To expose this overlooked vulnerability, we introduce a Coherence-Preserving Semantic Injection (CSI) attack that leverages LLM-guided semantic manipulation under embedding-space similarity constraints. This alignment enforces visual-semantic consistency while selectively perturbing watermark-relevant semantics, ultimately inducing detector misclassification. Extensive empirical results show that CSI consistently outperforms prevailing attack baselines against content-aware semantic watermarking, revealing a fundamental security weakness of current semantic watermark designs when confronted with LLM-driven semantic perturbations.
Generalized Category Discovery (GCD) is a critical task in open-world computing scenarios, aiming to automatically classify partially labeled data by recognizing both known and novel categories. However, existing GCD methods usually suffer from inherent bias toward known categories due to the exclusive pre-training on them and the absence of labeled data of novel categories. This bias can lead to significant misclassification and clustering errors for novel categories. Although recent approaches leverage pseudo-label training and contrastive learning to address this, they still lack explicit supervision to disentangle novel and known categories, resulting in performance bottlenecks. To address these limitations, we propose an Expectation-Maximization-driven Contrastive Disentanglement (EMCD) framework designed to explicitly disentangle novel and known categories. We particularly formulate the identification of novel categories as a latent variable estimation problem. Specifically, it incorporates an EM-disentangling regularization to softly identify novel category samples and a consistency regularization to enhance generalization. In addition, we leverage dual contrastive constraints, including a cluster-sample contrastive constraint and a sample-sample contrastive contrastive, to pull close samples of novel categories while pushing apart ambiguous samples near decision boundaries. Empirical results on 3 commonly used datasets demonstrate that our model is effective and outperforms previous state-of-the-art methods. Our code is available at https://github.com/YWY-only/EMCD.
Although extensive research has examined social media nudges to influence privacy, comparably less work investigates mechanisms of peer-to-peer influence, or the ways in which peer groups can amplify or dampen privacy considerations. This study takes an experimental approach to examining how people are influenced to share potentially sensitive photos of others without consent---a common practice on social media---by comparing the effects of encouraging, discouraging, or mixed feedback social media comments. The results show that discouraging peer comments reduce the sharing of others' photos when content portrayed targets negatively. However, peer influence backfired among users with a history of online misconduct, with both encouraging and discouraging comments leading to more photo sharing. Moreover, a mix of comments that both discouraged and encouraged sharing led to the highest levels of sharing. Linking to prior work, this research establishes a broader understanding of when privacy nudges are likely to backfire on social media: for users with past online misconduct and when information goes against social norms. The findings advance understanding of how peer-to-peer dynamics shape online information flows and highlight the complex effects of Web-based social feedback on privacy decisions. These insights provide actionable design recommendations for platforms to foster responsible, privacy-conscious sharing norms.
Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the nuanced relationship between a citation's context and its place in the wider network. While large language models (LLMs) offer powerful capabilities in semantic reasoning for this task, their deployment is hindered by hallucination risks and high computational costs. In this work, we introduce LLM-Augmented Graph Learning-based Miscitation Detector (LAGMiD), a novel framework that leverages LLMs for deep semantic reasoning over citation graphs and distills this knowledge into graph neural networks (GNNs) for efficient and scalable miscitation detection. Specifically, LAGMiD introduces an evidence-chain reasoning mechanism, which uses chain-of-thought prompting, to perform multi-hop citation tracing and assess semantic fidelity. To reduce LLM inference costs, we design a knowledge distillation method aligning GNN embeddings with intermediate LLM reasoning states. A collaborative learning strategy further routes complex cases to the LLM while optimizing the GNN for structure-based generalization. Experiments on three real-world benchmarks show that LAGMiD achieves state-of-the-art miscitation detection with significantly reduced inference cost.
Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a prevalent yet underexplored phenomenon in graph generalization, Minimal Shift Flip (MSF)—where test samples that slightly deviate from the training distribution are abruptly misclassified. To interpret this phenomenon, we revisit MSF through the lens of Sharpness-Aware Minimization (SAM), which characterizes the local stability and sharpness of the loss landscape while providing a theoretical foundation for modeling generalization error. To quantify loss sharpness, we introduce the concept of Local Robust Radius, measuring the smallest perturbation required to flip a prediction and establishing a theoretical link between local stability and generalization. Building on this perspective, we further observe a continual decrease in the robust radius during training, indicating weakened local stability and an increasingly sharp loss landscape that gives rise to MSF. To jointly solve the MSF phenomenon and the intractability of radius, we develop an energy-based formulation that is theoretically proven to be monotonically correlated with the robust radius, offering a tractable and principled objective for modeling flatness and stability. Building on these insights, we propose an energy-driven generative augmentation framework (E2A) that leverages energy-guided latent perturbations to generate pseudo-OOD samples and enhance model generalization. Extensive experiments across multiple benchmarks demonstrate that E2A consistently improves graph OOD generalization, outperforming state-of-the-art baselines. Code is available at https://github.com/anders1123/E2A
Anomalous graphs, representing rare but critical deviations from normal graphs, frequently arise in high-stakes domains such as malicious website detection. Detecting them is highly challenging due to two key issues: (i) labeled anomalous graphs are extremely limited and fail to capture the diversity of real-world abnormality, restricting detection models from generalizing to unseen anomalies encountered in the open world, and (ii) normal graphs often contain spurious or atypical substructures that do not indicate anomalies but may induce models to misclassify normal variations as anomalies. To tackle these challenges, we propose G-GLAD, a generalizable graph-level anomaly detection framework. G-GLAD introduces two key innovations: (1) prompt-based anomaly space expansion, which injects learnable prompts into the graph representation process of known anomalies to simulate diverse unseen anomalous variants. This allows the model to learn a richer and more generalizable anomaly space; and (2) subgraph-based normality extraction, guided by the Information Bottleneck Principle, which isolates essential substructures for normality prediction while filtering out spurious motifs, improving robustness against structural noise. We conduct extensive experiments on ten real-world graph datasets under different empirical settings. The results demonstrate that G-GLAD achieves superior performance and generalizability in identifying anomalous graphs.
Defending against backdoor attacks on graphs has become increasingly critical. Existing methods predominantly focus on detecting and removing triggers by identifying inconsistencies between trigger and clean nodes. However, adversaries can design triggers that closely resemble clean nodes, making them challenging to detect. Therefore, understanding the mechanisms underlying backdoor attacks is crucial. In this work, we observe an interesting phenomenon: in backdoored models, specific ''backdoor neurons'' (embedding dimensions) are more likely to be activated, causing nodes to be misclassified to the target label. This is largely due to the graph structure, where malicious information propagates through node neighborhoods, activating specific neurons and target label. Based on this observation, we theoretically and empirically demonstrate how graph backdoor attacks exploit this propagation mechanism to effectively poison the target node's embedding. Meanwhile, we propose a novel defense called Graph Backdoor Neuron Defense (GBND) to identify, unlearn, and recover backdoor neurons. Specifically, we design a novel reverse engineering technique to identify triggers that activate backdoor neurons, and eliminate their harmful effects by asymmetric unlearning and recovering at the neuron level. Extensive experiments on four datasets validate the effectiveness of GBND in defending against backdoor attacks.
High dialogue engagement is a crucial indicator of an effective conversation. A reliable measure of engagement could help benchmark large language models, enhance the effectiveness of human-computer interactions, or improve personal communication skills. However, quantifying engagement is challenging, since it is subjective and lacks a ''gold standard''. This paper proposes PMIScore, an efficient unsupervised approach to quantify dialogue engagement. It uses pointwise mutual information (PMI), which is the probability of generating a response conditioning on the conversation history. Thus, PMIScore offers a clear interpretation of engagement. As directly computing PMI is intractable due to the complexity of dialogues, PMIScore learned it through a dual form of divergence. The algorithm includes generating positive and negative dialogue pairs, extracting embeddings by large language models (LLMs), and training a small neural network using a mutual information loss function. We validated PMIScore on both synthetic and real-world datasets. Our results demonstrate the effectiveness of PMIScore in PMI estimation and the reasonableness of the PMI metric itself.
Clinical prediction increasingly relies on multi-modal inputs, where reliability and efficiency are crucial for real-world deployment. However, mainstream fusion and MoE gating typically treat all available modalities as uniformly beneficial and allow noisy or weakly informative modalities to perturb routing, leading to instability, routing collapse, and miscalibrated confidence under missingness and shift. We propose QA-MoE, a Quality-Aware and stable multimodal Mixture-of-Experts that decouples reliability estimation from routing to enable robust, sparse, and interpretable fusion. QA-MoE adopts a modular architecture where each modality is initially encoded into a shared embedding space. To deal with structurally missing data, we employ a completion pathway that maintains a consistent interface. Unlike standard approaches, QA-MoE separates reliability estimation from the routing process. We propose an Evidential Quality Scorer to measure epistemic uncertainty, which then guides a Stability-Enhanced Subset Selector to filter out noisy modalities on the fly. Additionally, we include a Ternary Expert Aggregation mechanism acting as a specialized branch to stabilize predictions when data missingness is severe. Evaluations on clinical benchmarks (ADNI for Alzheimer’s staging and MIMIC-IV for Length-of-Stay) demonstrate that QA-MoE outperforms strong multimodal baselines, improving reliability while cutting down unnecessary computation. This indicates that QA-MoE offers a robust solution for multimodal decision support, especially in clinical settings prone to noise and missing data.
Vertical Federated Learning (VFL) involves multiple participants collaborating to train machine learning models on distinct feature sets from the same data samples. This training paradigm with distributed updating focuses on secure and efficient communication. Nevertheless, the trained models exhibit heightened vulnerability to adversarial attacks during inference, which can provoke misclassification. Adversarial Training (AT), which involves exposing models to intentionally crafted misleading examples during training, is widely regarded as the most effective method for enhancing model robustness. However, the significant communication costs entailing such example generation within the VFL context pose an open challenge to developing a Vertical Federated Adversarial Learning (VFAL) framework. To this end, we introduce a Communication-Efficient Vertical Federated Adversarial Learning framework, named CE-VFAL. CE-VFAL framework incorporates the lazy propagation principle, confining most propagations to client models during adversarial updates, thereby minimizing frequent client-server interactions. Moreover, CE-VFAL seamlessly integrates Zeroth Order Optimization (ZOO) into communication, effectively reducing communication load by transmitting the loss difference derived from the raw and perturbed embeddings for multiple point estimation. Furthermore, our theoretical analysis demonstrates the sublinear convergence rate by containing the errors caused by multi-source approximate gradients. Extensive experiments corroborate the robust performance while significantly reducing communication costs.
Reward learning via human feedback is a crucial capability for beneficial AI. Current methods are built on decision-making theories that assume a matched dynamics model between the learning agent and the feedback provider. However, humans often form imperfect internal dynamics models, and their feedback reflects these misconceptions. While this relationship has long been hypothesised, its manifestation in sequential decision-making remains largely an assumption. Our work provides the first comprehensive empirical investigation of this relationship through a randomized controlled trial (N=211). We followed a two-stage design where we first initialized the participants' understanding of the dynamics in a grid-world navigation domain and then manipulated it using text-based instructions. Causal mediation analysis revealed that humans' internal models play a mediating role in feedback behaviour. We show that this relationship is invariant across visual contexts and is robust to three common feedback types: pairwise preferences, trajectory corrections, and off-switch interventions. These findings confirm a critical limitation of current reward learning methods and establish the missing psychological foundation for approaches that incorporate dynamics understanding.
Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where models behave normally on clean data but exhibit targeted misclassifications once specific triggers are activated. Existing backdoor attacks on GNNs mainly focus on enhancing trigger stealthiness or diversifying attack paradigms. However, these methods overlook a fundamental property of GNNs: trigger-induced malicious signals inevitably propagate through graph neighborhoods, causing unintended mispredictions on clean nodes, i.e., Collateral Damage. To address this issue, we propose the Collateral Damage Constrained Graph Backdoor Attack (CDCA), a novel framework that explicitly controls malicious diffusion. Specifically, the proposed method combines neighborhood-aware target node selection with a self-constrained trigger generation strategy to suppress trigger-induced propagation by enforcing prediction consistency on clean K-hop neighboring nodes. Extensive experiments on real-world datasets demonstrate that the proposed method remains effective while significantly reducing collateral damage.
Adversarial training is an effective technique for enhancing the robustness of deep neural networks (DNNs). Prior research shows that misclassified examples influence final adversarial robustness much more than correctly classified examples. Ignoring this difference during training can hurt model performance. In crowdsourcing, varying annotator expertise causes noisy, inconsistent labels. As a result, it is hard to distinguish misclassified and correctly classified examples using only provided annotations. Thus, how to use the reliability and discrepancy between these example types to improve robustness within adversarial learning remains a critical but underexplored issue. In this work, we first explore how misclassified and correctly classified examples affect learning from crowds (LFC) in adversarial environments. Then, we formulate the problem of misclassification-aware robust learning from multiple human labelers as a bilevel min-max problem. After that, we introduce MALC, a new approach to make classifiers more robust to adversarial examples via iterative adversarial example generation and parameter estimation. We conduct an extensive evaluation of the proposed MALC, showing that MALC can outperform the state-of-the-art LFC methods in both white-box and black-box settings.
An Explanation-Based Classroom Response System for Real-Time Analysis of Undergraduate Students’ Natural Language Explanations
PDF ↗Effective classroom teaching requires instructors to be responsive to their students, such as by pivoting their lectures in real-time to address common misconceptions that their students may have developed. Classroom response systems such as multiple-choice "clicker" systems are one method by which instructors can gauge their students’ understanding during classroom lectures, but open-ended questions that prompt students to engage in self-explanation are better suited to promoting critical thinking. Additionally, analyzing students’ natural language responses typically requires time-consuming manual analysis, which makes it challenging to implement in a classroom setting. To address this challenge, we present an LLM-driven method for automatically assessing students' responses and generating an aggregated summary of LLM-based evaluations for their self-explanations during undergraduate classroom lectures. Our approach extracts relevant knowledge components for a given question, tags students’ responses according to whether they correctly address each knowledge component, and generates class-level summaries that highlight common misconceptions and gaps in knowledge to support instructors in pivoting their lectures in real time. We evaluate the system’s effectiveness at these tagging and summarization tasks on data from an undergraduate computer science course, using quantitative and qualitative metrics such as relevance, sufficiency, hallucination rate, and alignment with instructional goals and desired feedback format gathered through instructor interviews. Results suggest that the explanation-based classroom response system can accurately analyze students’ natural language explanations.
Breakable Machine: A K–12 Classroom Game for Transformative AI Literacy Through Spoofing and eXplainable AI (XAI)
PDF ↗This paper presents an eXplainable AI (XAI)-based classroom game “Breakable Machine” for teaching critical, transformative AI literacy through adversarial play and interrogation of AI systems. Designed for learners aged 10–15, the game invites students to spoof an image classifier by manipulating their appearance or environment in order to trigger high-confidence misclassifications. Rather than focusing on building AI models, this activity centers on breaking them—exposing their brittleness, bias, and vulnerability through hands-on, embodied experimentation. The game includes an XAI view to help students visualize feature saliency, revealing how models attend to specific visual cues. A shared classroom leaderboard fosters collaborative inquiry and comparison of strategies, turning the classroom into a site for collective sensemaking. This approach repositions AI education by treating model failure and misclassification not as problems to be debugged, but as pedagogically rich opportunities to interrogate AI as a sociotechnical system. In doing so, the game supports students in developing data agency, ethical awareness, and a critical stance toward AI systems increasingly embedded in everyday life.
Impact of a Data-driven Teaching Approach on 9th Graders Conceptual Understanding of Machine Learning
PDF ↗This study aimed to investigate the impact of a data-driven teaching approach on students’ conceptual understanding of machine learning (ML). To this end, an exemplary intervention was designed and evaluated using a pre- and post-test design and a German-language Concept Inventory on Machine Learning. A total of 83 German ninth-grade students participated in the study. The results revealed significant learning gains related to data handling and the ML workflow. In contrast, conceptions about the inner workings of ML models largely persisted. The effectiveness of the intervention varied depending on context, with greater gains observed in the text generation domain than in facial recognition, highlighting challenges in cross-contextual transfer of understanding. A regression analysis showed no significant influence of students’ pre-instructional conceptions on learning outcomes. These findings demonstrate both the potential and the limitations of data-driven teaching approaches and emphasize the need for more explicit engagement with learners' misconceptions to foster deeper conceptual change.
Multiple-choice questions (MCQs) are central to instruction and assessment, with distractors revealing student understanding and misconceptions. However, creating high-quality distractors is time-consuming, especially for emerging domains like K–12 AI education. This study explores using generative AI to support distractor creation in a self-paced online module integrating AI and Algebra 1. Five MCQs were selected to compare distractors written by human developers and ChatGPT, using expert reviews and log data from 80 students. Experts rated human distractors higher overall, though AI ones consistently ranked second. Log analysis showed human distractors drew more initial selections, while students who chose AI distractors spent more time engaging without differences in hint use or revisits. Transition patterns across attempts suggest AI-generated distractors can effectively guide students toward correct answers, highlighting their potential for scalable MCQ design.
‘What Do Children Think About AI?’: Insights and Educational Implications from Primary School Students’ Perceptions of AI
PDF ↗AI has great potential to transform education and daily life. However, before integrating AI into classrooms, it is crucial to first educate children on what AI is and how to use it responsibly. Effective AI education should build on children's existing perceptions, address misconceptions, and establish a solid foundation for AI literacy. This study explores primary school students’ perception of AI and its relationship to their demographic characteristics and digital skills. A survey was conducted in seven local schools, with 233 students participating. The results indicate that most of them were unfamiliar with AI, and those who attempted to define or depict it often associated it with robots or digital devices. The study also found significant differences in students’ AI perceptions based on factors like gender, grade, and prior digital skills training. These variables were also linked to students’ awareness and understanding of AI. These findings underscore the need for targeted AI educational interventions for primary school students, leveraging their existing perceptions.