1273993 results (page 119 of 50960)
-
Deflection of a Filament Eruption with Three Parallel Flare Ribbons via Reconnection at an X-Point
On 2024 May 6, Active Region 13663 produced an X4.5-class flare associated with a filament eruption that exhibited remarkable rotation and deflection dynamics. This study aims to investigate two key aspects of this event: the formation mechanisms of the complex flare ribbon structures and the physical drivers behind the observed filament deflection. We conduct a data-constrained magnetohydrodynami…
-
Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts
Deep learning (DL)-based systems can exhibit unexpected behavior when exposed to out-of-distribution (OOD) scenarios, posing serious risks in safety-critical domains such as malware detection and autonomous driving. This underscores the importance of thoroughly testing such systems before deployment. To this end, researchers have proposed a wide range of test selection metrics designed to effectiv…
-
Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards
The deployment of Large Language Models (LLMs) as assistants in electric grid operations promises to streamline compliance and decision-making but exposes new vulnerabilities to prompt-based adversarial attacks. This paper evaluates the risk of jailbreaking LLMs, i.e., circumventing safety alignments to produce outputs violating regulatory standards, assuming threats from authorized users, such as…
-
Can LLMs be Effective Code Contributors? A Study on Open-source Projects
LLM-generated code is widely used, and the share of committed code produced by LLMs is expected to increase. However, we are not at a point where LLMs can be effective contributors to production code. We present an approach that exposes the shortcomings of LLM generation on such projects, and proposes recommendations; the targets of our study are sizable open-source projects, e.g., FFmpeg and wolf…
-
From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems
Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer agents. Existing security analyses organize threats by attack type (prompt injection, jailbreaking), but provide no principled model of which architectural component is vulnerable or over what timesc…
-
Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose Rabtriever, which independently encodes queries and documents, while providing comparable cross query-document comprehension capabilities to rerankers. We start…
-
H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading
Knee osteoarthritis (KOA) is a degenerative joint disease that can lead to chronic pain, reduced mobility, and long-term disability. Automated severity grading from knee radiographs can support early assessment, but current methods heavily depend on large labeled datasets and remain sensitive to class imbalance, noisy samples, and variability in clinical annotations. To alleviate these limitations…
-
A Note on Interdiction of Linear Minimization Problems
Motivated by the FPTAS for connectivity interdiction of Huang et al. (IPCO'24), we isolate the part of the argument that does not use cuts. The setting is a minimization problem over a feasible-set family $\mathcal F$ with a linear objective $w(S)=\sum_{e\in S}w(e)$. After dualizing the interdiction budget, deletion can be absorbed into truncated weights $w_λ(e)=\min\{w(e),λc(e)\}$. At an optimal …
-
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to hallucinations, unreliable confidence-based control, and unnecessary compute allocation. We introduce Reinforcement Learning with Confidence Margin (\textbf{RLCM}),…
-
Advanced Anomaly Detection and Threat Intelligence in Zero Trust IoT Environments Using Machine Learning
The growing adoption of IoT and cloud computing, combined with rapid advancements in digital technologies, has considerably increased the cyber-attack surface, resulting in increasingly complex and persistent attacks. Traditional security methods, primarily based on perimeter defenses, are insufficient to meet these developing threats, especially within the context of a Zero Trust Security (ZTS) a…
-
Branch Landing: Bloom Filter-Based Source Authorization for Forward-Edge CFI on RISC-V
Jump-Oriented Programming (JOP) attacks exploit indirect control transfers to bypass backward-edge defenses, yet existing forward-edge CFI mechanisms lack precise source-domain authorization: type-based CFI admits all same-signature callers, while tag-based hardware CFI is limited by fixed-width register storage that caps the number of simultaneously authorized sources. We propose Branch Landing (…
-
An Efficient Beam Search Algorithm for Active Perception in Mobile Robotics
Active perception is a fundamental problem in autonomous robotics in which the robot must decide where to move and what to sense in order to obtain the most informative observations for accomplishing its mission. Existing approaches either solve a computationally expensive traveling salesman problem over heuristically selected informative nodes, or adopt a more efficient but overly constrained sho…
-
EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence
Emotionally talking head video generation aims to generate expressive portrait videos with accurate lip synchronization and emotional facial expressions. Current methods rely on simple emotional labels, leading to insufficient semantic information. While introducing high-level semantics enhances expressiveness, it easily causes lip-sync degradation. Furthermore, mainstream generation methods strug…
-
Layer Embedding Deep Fusion Graph Neural Network
Graph Neural Networks (GNNs) have demonstrated impressive performance in learning representations from graph-structured data. However, their message-passing mechanism inherently relies on the assumption of label consistency among connected nodes, limiting their applicability to low-homophily settings. Moreover, since message passing operates as a hierarchical diffusion process, GNNs face challenge…
-
Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss
Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with long, noisy, and weakly labeled audio due to their reliance on contrastive learning and large-batch training. We propose a novel multimodal retrieval framework th…
-
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it difficult to systematically evaluate full-modality representation learning. In this work, we take a step toward the full-modality setting. We introduce MMEB-V3, a c…
-
KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition
The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based on the Kolmogorov-Arnold representation theorem, have shown potential to replace Multi-Layer Perceptrons (MLPs) in deep learning. KANs, which use learnable nonlinear activations on edges and simple summation on nodes, of…
-
Revisit viscous shock tube at low Reynolds number
The viscous shock tube is a canonical test case for assessing Navier-Stokes (NS) solvers in the continuum-flow regime, widely used to validate numerical accuracy and probe flow physics. It features a rich set of interacting structures-shock and rarefaction waves, contact discontinuities, boundary layers, and their coupling-spanning multiple spatial and temporal scales. However, NS-based modeling, …
-
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all tokens in a rollout. Process reward models can provide finer-grained supervision, but they require step-level annotation or additional reward modeling. We show that hidden-state distributions contain a useful signal for …
-
Multiplicative Contractions, Additive Recoveries: Functional-Form Restrictions on Risk Exposure Dynamics
We test a regime-conditional functional-form restriction on aggregate risk-exposure dynamics implied by VaR-constrained intermediary models: exposures contract multiplicatively when capital constraints bind and grow additively (level-independent) when slack. The contraction half follows from binding VaR constraints (Brunnermeier and Pedersen 2009; Adrian and Shin 2010; He and Krishnamurthy 2013). …
-
Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM
Segmentation is central to clinical diagnosis and monitoring, yet the reliability of modern foundation models in medical imaging still depends on the availability of precise prompts. The Segment Anything Model (SAM) offers powerful zero-shot capabilities, although it collapses under the weak, generic, and noisy prompts that dominate real clinical workflows. In practice, annotations such as centerl…
-
Risk-sensitive linear-quadratic-Gaussian graphon mean-field games
This paper investigates a class of linear-quadratic-Gaussian risk-sensitive graphon mean-field games, involving an asymptotically infinite population of heterogeneous agents distributed across an asymptotically infinite network, where each agent aims to minimize an exponential cost functional reflecting its risk sensitivity. Following the Nash certainty equivalence methodology, an auxiliary risk-s…
-
GIFT: Global stabilisation via Intrinsic Fine Tuning
Deep reinforcement learning policies achieve strong performance in complex continuous control environments with nonlinear contact forces. However, these policies often produce chaotic state dynamics, with trivially small changes to the initial conditions significantly impacting the long-term behaviour of the control system. This high sensitivity to initial conditions limits the application of Deep…
-
STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning
Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video modeling, they largely overlook the inherent ambiguities in viewpoint, scale, and prior knowledge, lacking effective constraints on the encoder. In this paper, we present STAND, a Semantic Anchoring Constraint with Dual-Granularity Disambiguatio…
-
CODA: Coordination via On-Policy Diffusion for Multi-Agent Offline Reinforcement Learning
Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data converge to suboptimal joint behaviours because they cannot co-adapt as their policies change. We introduce CODA (Coordination via On-Policy Diffusion for Multi-Agent Reinforcement Learning), a diffusion-based multi-agent tra…