arXiv subjects

Kai Wang

Publications and source records attributed to Kai Wang.

At least 271 records · Page 15Linked to original sources

arXiv2025

Neutron star phase transition as the origin for the fast radio bursts and soft gamma-ray repeaters of SGR J1935+2154

Magnetars are believed as neutron stars (NSs) with strong magnetic fields. X-ray flares and fast radio bursts (FRBs) have been observed from the magnetar (soft gamma-ray repeater, SGR J1935+2154). We propose that the phase transition of the NS can power the FRBs and SGRs.Based on the equation of state provided by the MIT bag model and the mean field approximation, we solve the Tolman-Oppenheimer-Volkoff equations to get the NS structure. With spin-down of the NS, the hadronic shell gradually transfers to the quark shell.The gravitational potential energy released by one time of the phase transition can be achieved. The released energy, time interval between two successive phase transitions, and glitch are all consistent with the observations of the FRBs and the X-ray flares from SGR J1935+2154. We conclude that the phase transition of an NS is a plausible mechanism to power the SGRs as well as the repeating FRBs.

astro-ph.HE↗

arXiv2025

TFLAG:Towards Practical APT Detection via Deviation-Aware Learning on Temporal Provenance Graph

Advanced Persistent Threat (APT) have grown increasingly complex and concealed, posing formidable challenges to existing Intrusion Detection Systems in identifying and mitigating these attacks. Recent studies have incorporated graph learning techniques to extract detailed information from provenance graphs, enabling the detection of attacks with greater granularity. Nevertheless, existing studies have largely overlooked the continuous yet subtle temporal variations in the structure of provenance graphs, which may correspond to surreptitious perturbation anomalies in ongoing APT attacks. Therefore, we introduce TFLAG, an advanced anomaly detection framework that for the first time integrates the structural dynamic extraction capabilities of temporal graph model with the anomaly delineation abilities of deviation networks to pinpoint covert attack activities in provenance graphs. This self-supervised integration framework leverages the graph model to extract neighbor interaction data under continuous temporal changes from historical benign behaviors within provenance graphs, while simultaneously utilizing deviation networks to accurately distinguish authentic attack activities from false positive deviations due to unexpected subtle perturbations. The experimental results indicate that, through a comprehensive design that utilizes both attribute and temporal information, it can accurately identify the time windows associated with APT attack behaviors without prior knowledge (e.g., labeled data samples), demonstrating superior accuracy compared to current state-of-the-art methods in differentiating between attack events and system false positive events.

cs.CR↗

arXiv2025

InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction

Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset.

cs.IR↗

arXiv2025

MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance

General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated multimodal datasets. To address this gap, we introduce MITS (Multimodal Intelligent Traffic Surveillance), the first large-scale multimodal benchmark dataset specifically designed for ITS. MITS includes 170,400 independently collected real-world ITS images sourced from traffic surveillance cameras, annotated with eight main categories and 24 subcategories of ITS-specific objects and events under diverse environmental conditions. Additionally, through a systematic data generation pipeline, we generate high-quality image captions and 5 million instruction-following visual question-answer pairs, addressing five critical ITS tasks: object and event recognition, object counting, object localization, background analysis, and event reasoning. To demonstrate MITS's effectiveness, we fine-tune mainstream LMMs on this dataset, enabling the development of ITS-specific applications. Experimental results show that MITS significantly improves LMM performance in ITS applications, increasing LLaVA-1.5's performance from 0.494 to 0.905 (+83.2%), LLaVA-1.6's from 0.678 to 0.921 (+35.8%), Qwen2-VL's from 0.584 to 0.926 (+58.6%), and Qwen2.5-VL's from 0.732 to 0.930 (+27.0%). We release the dataset, code, and models as open-source, providing high-value resources to advance both ITS and LMM research.

cs.CV↗

arXiv2025

Finding a Multiple Follower Stackelberg Equilibrium: A Fully First-Order Method

In this work, we propose the first fully first-order method to compute an epsilon stationary Stackelberg equilibrium with convergence guarantees. To achieve this, we first reframe the leader follower interaction as single level constrained optimization. Second, we define the Lagrangian and show that it can approximate the leaders gradient in response to the equilibrium reached by followers with only first-order gradient evaluations. These findings suggest a fully first order algorithm that alternates between (i) approximating followers best responses through gradient descent and (ii) updating the leaders strategy via approximating the gradient using Lagrangian.

math.OC↗

arXiv2025

Quantum Purification for Amplitude Damping Noise

Noise poses a fundamental challenge to quantum information processing, with amplitude-damping (AD) noise being particularly detrimental. Preserving high-fidelity quantum systems therefore relies critically on effective error correction and purification methods. In this work, we introduce a novel approach for mitigating AD noise that can be applied to both state and channel purification. Our method achieves a substantial enhancement in the fidelity of affected states or channels while maintaining a low resource overhead, requiring only one or two ancilla qubits in combination with two Clifford gates, and exhibits a relatively high success probability. This approach provides a practical and scalable framework for addressing AD noise in realistic quantum systems.

quant-ph↗

arXiv2025

Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Setting

Large Language Models (LLMs) are increasingly used for recommendation tasks due to their general-purpose capabilities. While LLMs perform well in rich-context settings, their behavior in cold-start scenarios, where only limited signals such as age, gender, or language are available, raises fairness concerns because they may rely on societal biases encoded during pretraining. We introduce a benchmark specifically designed to evaluate fairness in zero-context recommendation. Our modular pipeline supports configurable recommendation domains and sensitive attributes, enabling systematic and flexible audits of any open-source LLM. Through evaluations of state-of-the-art models (Gemma 3 and Llama 3.2), we uncover consistent biases across recommendation domains (music, movies, and colleges) including gendered and cultural stereotypes. We also reveal a non-linear relationship between model size and fairness, highlighting the need for nuanced analysis.

cs.IR↗

arXiv2025

Can Quasi-periodic Eruptions Produce Detectable High Energy Neutrinos?

Quasi-periodic eruptions (QPEs) are a class of X-ray flaring phenomena that occur at the centers of galactic nuclei and are likely to arise from repeated interactions between a star and an accretion disk. This work investigates whether such disk-crossing events can accelerate protons and generate detectable high-energy neutrinos. Based on observed QPE luminosities, recurrence periods, and flare durations, the stellar motion parameters and the disk properties are evaluated. We consider proton acceleration during the breakout phase and evaluate neutrino production, accounting for both $pp$ and $pγ$ interactions. Applying the method to ten observed QPE sources, we estimate the neutrino fluence accumulated over a 10-year observation period and compute the corresponding detection numbers for IceCube and IceCube-Gen2. Our analysis indicates that protons can be accelerated up to several tens of TeV, and neutrino production is mostly confined below $\sim 10~\mathrm{TeV}$. The resulting optimized neutrino fluence spans from $ 7.0 \times 10^{-7} $ to $1.5 \times 10^{-4}~\mathrm{GeV~cm^{-2}}$ for these ten QPE sources. We find that the expected neutrino detection number for a single QPE source is low, and the expected neutrino detection number would approach unity only for the most promising QPE source occurring at a distance closer than a few Mpc. Next-generation neutrino telescopes with better detection sensitivities at $\lesssim \rm TeV$ can significantly improve the capture capacity of the cumulative neutrino signal from the QPE population.

astro-ph.HE↗

arXiv2025

TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning

High-dimensional vector similarity search (HVSS) is critical for many data processing and AI applications. However, traditional HVSS methods often require extensive data access for distance calculations, leading to inefficiencies. Triangle-inequality-based lower bound pruning is a widely used technique to reduce the number of data access in low-dimensional spaces but becomes less effective in high-dimensional settings. This is attributed to the "distance concentration" phenomenon, where the lower bounds derived from the triangle inequality become too small to be useful. To address this, we propose TRIM, which enhances the effectiveness of traditional triangle-inequality-based pruning in high-dimensional vector similarity search using two key ways: (1) optimizing landmark vectors used to form the triangles, and (2) relaxing the lower bounds derived from the triangle inequality, with the relaxation degree adjustable according to user's needs. TRIM is a versatile operation that can be seamlessly integrated into both memory-based (e.g., HNSW, IVFPQ) and disk-based (e.g., DiskANN) HVSS methods, reducing distance calculations and disk access. Extensive experiments show that TRIM enhances memory-based methods, improving graph-based search by up to 90% and quantization-based search by up to 200%, while achieving a pruning ratio of up to 99%. It also reduces I/O costs by up to 58% and improves efficiency by 102% for disk-based methods, while preserving high query accuracy.

cs.DB↗

arXiv2025

Topological Amplification of the Bosonic Kitaev Chain with Non-Uniform Loss

The bosonic Kitaev chain is known to have extraordinary properties distinct from its fermionic counterpart. For example, it exhibits the non-Hermitian skin effect -- its eigenmodes are exponentially localized to the edges of the chain -- even when the system is Hermitian. Such non-Hermitian effects originate from the fact that the dynamics of bosonic quadratic Hamiltonians is governed by a non-Hermitian matrix. In the topological phase of the model, the modes conspire to lead to phase-dependent and directional exponential amplification of a classical drive. In this work, we study the robustness of this topological amplification to on-site dissipations. We examine the effect of uniform and non-uniform losses under various configurations. We find a remarkable resilience to dissipation in some configurations, while in others the dissipation causes a topological phase transition which eliminates the exponential amplification. In particular, when the dissipation is placed on every other site, the system remains topological and the exponential amplification persists even for very large loss rates which exceed the system's non-Hermitian gap. On the other hand, we find that dividing the chain into unit cells of an odd number of sites and placing dissipation on the first site leads to a topological phase transition at a certain critical value of the dissipation. Our work thus provides insights into the robustness against losses of the topological amplification of non-Hermitian systems and sets explicit limits on the bosonic Kitaev chain's ability to act as a multimode quantum sensor in realistic lossy scenarios.

cond-mat.mes-hall↗

arXiv2025

SoK: Understanding the Fundamentals and Implications of Sensor Out-of-band Vulnerabilities

Sensors are fundamental to cyber-physical systems (CPS), enabling perception and control by transducing physical stimuli into digital measurements. However, despite growing research on physical attacks on sensors, our understanding of sensor hardware vulnerabilities remains fragmented due to the ad-hoc nature of this field. Moreover, the infinite attack signal space further complicates threat abstraction and defense. To address this gap, we propose a systematization framework, termed sensor out-of-band (OOB) vulnerabilities, that for the first time provides a comprehensive abstraction for sensor attack surfaces based on underlying physical principles. We adopt a bottom-up systematization methodology that analyzes OOB vulnerabilities across three levels. At the component level, we identify the physical principles and limitations that contribute to OOB vulnerabilities. At the sensor level, we categorize known attacks and evaluate their practicality. At the system level, we analyze how CPS features such as sensor fusion, closed-loop control, and intelligent perception impact the exposure and mitigation of OOB threats. Our findings offer a foundational understanding of sensor hardware security and provide guidance and future directions for sensor designers, security researchers, and system developers aiming to build more secure sensors and CPS.

cs.CR↗

arXiv2025

Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee

Online restless multi-armed bandits (RMABs) typically assume that each arm follows a stationary Markov Decision Process (MDP) with fixed state transitions and rewards. However, in real-world applications like healthcare and recommendation systems, these assumptions often break due to non-stationary dynamics, posing significant challenges for traditional RMAB algorithms. In this work, we specifically consider $N$-armd RMAB with non-stationary transition constrained by bounded variation budgets $B$. Our proposed \rmab\; algorithm integrates sliding window reinforcement learning (RL) with an upper confidence bound (UCB) mechanism to simultaneously learn transition dynamics and their variations. We further establish that \rmab\; achieves $\widetilde{\mathcal{O}}(N^2 B^{\frac{1}{4}} T^{\frac{3}{4}})$ regret bound by leveraging a relaxed definition of regret, providing a foundational theoretical framework for non-stationary RMAB problems for the first time.

cs.LG↗

arXiv2025

CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection

With the rapid advancement of AI generative models, the visual quality of AI-generated images (AIIs) has become increasingly close to natural images, which inevitably raises security concerns. Most AII detectors often employ the conventional image classification pipeline with natural images and AIIs (generated by a generative model), which can result in limited detection performance for AIIs from unseen generative models. To solve this, we proposed a universal AI-generated image detector from the perspective of anomaly detection. Our discriminator does not need to access any AIIs and learn a generalizable representation with unsupervised learning. Specifically, we use the pre-trained CLIP encoder as the feature extractor and design a normalizing flow-like unsupervised model. Instead of AIIs, proxy images, e.g., obtained by applying a spectral modification operation on natural images, are used for training. Our models are trained by minimizing the likelihood of proxy images, optionally combined with maximizing the likelihood of natural images. Extensive experiments demonstrate the effectiveness of our method on AIIs produced by various image generators.

cs.CV↗

arXiv2025

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

We present TAR3D, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT) to generate high-quality 3D assets. The core insight of this work is to migrate the multimodal unification and promising learning capabilities of the next-token prediction paradigm to conditional 3D object generation. To achieve this, the 3D VQ-VAE first encodes a wide range of 3D shapes into a compact triplane latent space and utilizes a set of discrete representations from a trainable codebook to reconstruct fine-grained geometries under the supervision of query point occupancy. Then, the 3D GPT, equipped with a custom triplane position embedding called TriPE, predicts the codebook index sequence with prefilling prompt tokens in an autoregressive manner so that the composition of 3D geometries can be modeled part by part. Extensive experiments on ShapeNet and Objaverse demonstrate that TAR3D can achieve superior generation quality over existing methods in text-to-3D and image-to-3D tasks

cs.CV↗

arXiv2025

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction

Novel view synthesis (NVS) is a cornerstone for image-to-3d creation. However, existing works still struggle to maintain consistency between the generated views and the input views, especially when there is a significant camera pose difference, leading to poor-quality 3D geometries and textures. We attribute this issue to their treatment of all target views with equal priority according to our empirical observation that the target views closer to the input views exhibit higher fidelity. With this inspiration, we propose AR-1-to-3, a novel next-view prediction paradigm based on diffusion models that first generates views close to the input views, which are then utilized as contextual information to progressively synthesize farther views. To encode the generated view subsequences as local and global conditions for the next-view prediction, we accordingly develop a stacked local feature encoding strategy (Stacked-LE) and an LSTM-based global feature encoding strategy (LSTM-GE). Extensive experiments demonstrate that our method significantly improves the consistency between the generated views and the input views, producing high-fidelity 3D assets.

cs.CV↗

arXiv2025

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

Text-to-image generation has seen groundbreaking advancements with diffusion models, enabling high-fidelity synthesis and precise image editing through cross-attention manipulation. Recently, autoregressive (AR) models have re-emerged as powerful alternatives, leveraging next-token generation to match diffusion models. However, existing editing techniques designed for diffusion models fail to translate directly to AR models due to fundamental differences in structural control. Specifically, AR models suffer from spatial poverty of attention maps and sequential accumulation of structural errors during image editing, which disrupt object layouts and global consistency. In this work, we introduce Implicit Structure Locking (ISLock), the first training-free editing strategy for AR visual models. Rather than relying on explicit attention manipulation or fine-tuning, ISLock preserves structural blueprints by dynamically aligning self-attention patterns with reference images through the Anchor Token Matching (ATM) protocol. By implicitly enforcing structural consistency in latent space, our method ISLock enables structure-aware editing while maintaining generative autonomy. Extensive experiments demonstrate that ISLock achieves high-quality, structure-consistent edits without additional training and is superior or comparable to conventional editing techniques. Our findings pioneer the way for efficient and flexible AR-based image editing, further bridging the performance gap between diffusion and autoregressive generative models. The code will be publicly available at https://github.com/hutaiHang/ATM

cs.CV↗

arXiv2025

MDK12-Bench: A Comprehensive Evaluation of Multimodal Large Language Models on Multidisciplinary Exams

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs suffer from limited scale, narrow coverage, and unstructured knowledge, offering only static and undifferentiated evaluations. To bridge this gap, we introduce MDK12-Bench, a large-scale multidisciplinary benchmark built from real-world K-12 exams spanning six disciplines with 141K instances and 6,225 knowledge points organized in a six-layer taxonomy. Covering five question formats with difficulty and year annotations, it enables comprehensive evaluation to capture the extent to which MLLMs perform over four dimensions: 1) difficulty levels, 2) temporal (cross-year) shifts, 3) contextual shifts, and 4) knowledge-driven reasoning. We propose a novel dynamic evaluation framework that introduces unfamiliar visual, textual, and question form shifts to challenge model generalization while improving benchmark objectivity and longevity by mitigating data contamination. We further evaluate knowledge-point reference-augmented generation (KP-RAG) to examine the role of knowledge in problem-solving. Key findings reveal limitations in current MLLMs in multiple aspects and provide guidance for enhancing model robustness, interpretability, and AI-assisted education.

cs.AI↗

arXiv2025

A dataset of primary nasopharyngeal carcinoma MRI with multi-modalities segmentation

Multi-modality magnetic resonance imaging(MRI) data facilitate the early diagnosis, tumor segmentation, and disease staging in the management of nasopharyngeal carcinoma (NPC). The lack of publicly available, comprehensive datasets limits advancements in diagnosis, treatment planning, and the development of machine learning algorithms for NPC. Addressing this critical need, we introduce the first comprehensive NPC MRI dataset, encompassing MR axial imaging of 277 primary NPC patients. This dataset includes T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, totaling 831 scans. In addition to the corresponding clinical data, manually annotated and labeled segmentations by experienced radiologists offer high-quality data resources from untreated primary NPC.

eess.IV↗