Networking
Rethinking Web Application Firewalls
Laurin Brandner and Laurent Vanbever
In recent years, the threat of application-layer (L7) distributed denial-of-service (DDoS) attacks is ever increasing. To defend against them, network operators deploy web application firewalls (WAFs). WAFs are stateful scoring systems which are configured with a rule set that specifies what malicious traffic looks like, and how to handle it. While effective, WAFs are expensive and can increase the request latency of realistic applications by up to $4\times$. This paper introduces Shimmer, a highly optimized WAF. Shimmer JIT-compiles the rule set and applies advanced optimizations to avoid unnecessary work in the scoring pipeline.
Read the full abstract ▾
Computer Vision
BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception
Zihan Chen, Hengguang Zhou, Yuan Kang et al. (+5 more)
Multimodal large
language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may only appear in local regions. On-policy self-
distillation (OPD) enables transferring privileged visual knowledge from informative views to full-image policies, but querying the teacher for every rollout introduces substantial supervision costs. In this work, we propose BAS-OPD, a budget-aware selective OPD framework that allocates teacher supervision under limited query budgets. Instead of querying all rollouts, BAS-OPD selects informative samples while maintaining full-batch student generation. We explore random, uncertainty-based, and learned utility-based selection strategies, where the learned selector estimates query value from detached rollout statistics and online utility signals derived from student–teacher agreement and teacher confidence without additional student forward passes. BAS-OPD only changes training-time supervision allocation and preserves single-pass full-image inference. Experiments on fine-grained
multimodal perception
benchmarks demonstrate that BAS-OPD achieves strong performance while substantially reducing teacher supervision costs, highlighting the effectiveness of selective OPD under constrained budgets.
Read the full abstract ▾
All authors Zihan Chen, Hengguang Zhou, Yuan Kang, Yiming Zhang, Wenhui Fang, Zenghui Ding, Yining Sun, Cho-Jui Hsieh
Computation and Language
Rethinking Length-Based Training: Batch Composition and Loss Normalization in Speech Token Language Models
Hongjin Song, Runwu Shi, Weiqiao Shan et al. (+4 more)
Short-to-long training is a simple curriculum for
speech models, but its gains can be difficult to interpret. In
speech token language models, length-based training can change the shuffle policy, batch composition,
token retention, and
token weights under batch-mean loss. We disentangle these factors through matched comparisons. In the tested settings, short-to-long ordering shows no independent benefit when batch composition and
token exposure are fixed. First-epoch grouping lowers perplexity for Mimi under batch-mean loss, but this gain is not observed under
token-balanced loss. The cross-tokenizer results are consistent with a link between chunk-length variation and
token weighting. This work provides a systematic analysis protocol for studying length-based training in variable-length
speech models.
Read the full abstract ▾
All authors Hongjin Song, Runwu Shi, Weiqiao Shan, Jiale Luo, Yujin Wang, Yifei Wu, Chunxiang Jin
Artificial Intelligence · Cross-listed from eess.SP
Risk-Aware Online Conformal State Probing
Pietro Talli, Petar Popovski and Osvaldo Simeone
AI-based autonomous
agents, typically hosted at data centers, must acquire state information from
robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in safety-critical settings, in which average-case guarantees are insufficient. In this context, we study a sequential decision maker process that jointly decides which actions to take and when to probe given access to an arbitrary state prediction model. We propose online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions. OCSP is designed to provably control the missed query error (MQE), i.e., the fraction of instances where probing would have been beneficial, while minimizing the probing rate. OCSP can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning. We validate OCSP through numerical simulations to verify theoretical guarantees and to assess performance trade-offs as a function of the calibration of the state predictor.
Read the full abstract ▾
Robotics
What is the Better Curriculum: Controller-Shaped Grasping Behavior for Contact Force-Sensitive Manipulation
Ziyan Feng, Zizhao Yuan, Yulong Fu et al. (+6 more)
How should a
robot learn to manipulate objects so fragile that sub-Newton contact forces can cause irreversible damage? Existing visuo-tactile policy learning typically treats tactile sensing as an additional policy input. In direct-contact force-sensitive manipulation, however, the bottleneck can arise earlier, during data collection: manual gripper control is too delayed and coarse-grained to reliably maintain the narrow force range required for stable grasping. We therefore use a deterministic 25 Hz tactile reflex controller as a collection-time teacher, producing demonstrations with controller-shaped grasping behavior for tactile-free policy learning. On Action Chunking with
Transformers (ACT), policies trained from reflex-shaped demonstrations recover the teacher's grasping profile and achieve 95% stable grasps on the nominal plastic-cup task, substantially outperforming visually screened manual demonstrations. The same intervention improves in-distribution stability on $\pi_{0.5}$ and shows a favorable exploratory trend on an unseen paper-cup variant. Under randomized external disturbance, however, the reflex-data $\pi_{0.5}$ policy still fails in 45% of policy-only trials, whereas a deployment-time reflex arbiter retains all grasps. These results reveal a new role for tactile feedback in force-sensitive manipulation: rather than integrating tactile into the policy, we use it as a collection-time teacher that shapes grasping behavior in demonstrations for policy learning, while disturbance rejection remains controller-dependent, revealing the boundary of tactile-free policy.
Read the full abstract ▾
All authors Ziyan Feng, Zizhao Yuan, Yulong Fu, Yuxin He, Zhiyuan Zhang, Zhengjie Zhang, Jinni Zhou, Renjing Xu, Qiang Nie
Cryptography and Security
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Jin Wei, Rundong Li, Ruihao Yang et al. (+10 more)
Users commonly combine multiple Low-Rank Adaptation (LoRA) adapters to personalize images with different subjects, styles, and visual attributes. Yet inspecting adapters individually does not establish the safety of their composition. We identify and characterize a pair-conditioned attack in text-to-image
diffusion: individually useful and benign-appearing adapters redirect image generation when co-loaded with a specifically matched partner, whose identity serves as the trigger. We introduce LoRango to realize this attack through complementary Signature and Payload adapters. The Signature writes a pair-specific code into intermediate carrier representations, while the Payload uses code-selective responses and opposing signal/reference branches. These branches approximately cancel for standalone adapters and mismatched pairs; matched code-reader
alignment breaks cancellation within native GEGLU blocks and releases the programmed action. Both adapters are exported as ordinary static LoRA files compatible with standard loaders, requiring no
prompt trigger or base-pipeline modification. LoRango achieves matched-pair attack success rates of 97.9% on SD v1.5 and 98.7% on SDXL, compared with 2.8–4.6% when implanted adapters are loaded individually. Further experiments evaluate pair selectivity, standalone fidelity, robustness to deployment variations, and applicability across denoiser architectures. These findings show that individual-adapter inspection is insufficient to assess the security of multi-LoRA personalization and motivate
auditing adapter compositions.
Read the full abstract ▾
All authors Jin Wei, Rundong Li, Ruihao Yang, Yikai Wang, Xiaoyuan Duan, Jianxiong Wu, Yanbo Wang, Chang Xu, Lingyun Zhang, Zhuyang Yu, Ping Chen, Jun Dai, Xiaoyan Sun
Human-Computer Interaction
The Impact of Deep Care Isa on Reducing Musculoskeletal Disorders and Enhancing Productivity Among Office Employees: A Comprehensive Study
Quanmin Liang, Junjie Yang, Mohammad Ali Nasseri et al. (+1 more)
Prolonged sedentary behavior, a pervasive issue in modern workplaces, has been closely linked to musculoskeletal disorders (MSDs) and reduced productivity. This study evaluates the effectiveness of Deep Care Isa, an advanced digital health assistant, in addressing these challenges. Utilizing data from over 2,300 participants across 50 corporations, the study demonstrates significant improvements in ergonomic practices, physical activity, hydration habits, and overall productivity, with notable reductions in MSD-related sick leave. The findings highlight the role of innovative ergonomic interventions in enhancing employee well-being and organizational efficiency. Comprehensive statistical analysis underscores the reliability and practical significance of these outcomes.
Read the full abstract ▾
All authors Quanmin Liang, Junjie Yang, Mohammad Ali Nasseri, Daniel Zapp
Cryptography and Security
COBRA: A Content-Agnostic Framework for Zero-Day Detection of Suspicious Domains
Alexandros Fourtounis, Emmanouil Papadogiannakis, Panagiotis Papadopoulos et al. (+2 more)
The use of malicious domains is central to cyberattacks such as phishing, malware distribution, impersonation, and fraudulent transactions. Because domains are inexpensive to register and easy to deploy at scale, they remain one of the most common and damaging tools used in cybercrime across industries. Proactive detection is essential to reducing this window of vulnerability and preventing harm to users. In this work, we propose COBRA: a content-agnostic, registration-time detection framework for identifying and analyzing suspicious domains from day zero. Our approach does not rely on any content-based features, allowing us to classify a domain even before it is populated with content. We analyze the names of newly registered domains and employ a clustering technique to group them based on lexical and structural similarity. We evaluate our methodology using real-world data consisting of 1.5M newly created domains, demonstrating that COBRA detects suspicious domains with a precision of 98.5%, identifying more than 47K distinct newly registered suspicious domains. Furthermore, our results show that domain-name clustering enables accurate early detection, allowing us to identify 80% of suspicious or malicious domains earlier than one of the most widely used threat-intelligence services, which in some cases may require up to 7 days.
Read the full abstract ▾
All authors Alexandros Fourtounis, Emmanouil Papadogiannakis, Panagiotis Papadopoulos, Nicolas Kourtellis, Evangelos Markatos
Computer Vision
Delving into Asymmetric Information Dynamics for High-Fidelity Virtual Try-On
Zishu Qin, Zhiyu Jin, Pipei Huang et al. (+1 more)
Virtual try-on (VTON) requires precise pixel-level fidelity, yet mainstream
Diffusion Transformers (DiTs) often suffer from texture degradation and structural drift. We identify symmetric interactions in standard joint-
attention mechanisms as a source of these failures. Although such interactions support semantic flexibility in general-purpose editing, they allow
stochastic noise to corrupt deterministic garment features in VTON. We analyze this problem through asymmetric information dynamics and introduce two diagnostic indicators: Conditional
Attention Entropy (CAE) for feature unbiasedness and Injected Information Flux (IIF) for injection effectiveness. Our analysis suggests that symmetric bidirectional
attention can corrupt conditional features and attenuate the conditional signal. To address these limitations, we propose RealFit, a framework that combines Unidirectional Information Flow (UIF) with Decoupled Timestep Modulation (DTM). UIF isolates the garment condition from
stochastic noise to preserve garment identity, while DTM optimizes the modulation scale to maintain a strong conditional signal. The resulting time-invariant condition branch enables a conditional KV cache that reduces inference time by approximately 75%. RealFit offers a principled approach to conditional generation with state-of-the-art fidelity and efficiency.
Read the full abstract ▾
All authors Zishu Qin, Zhiyu Jin, Pipei Huang, Hao Zhou
Systems and Control
High-Performance Sensorless Control for High-Speed PMSM with Current Source Inverters
Nail Tosun, Devinda Molligoda, Xu Deng et al. (+1 more)
Current source inverters (CSIs) are emerging as competitive alternatives to voltage source inverters (VSIs) for high-speed motor drives because they inherently suppress harmonic currents, offer output-voltage boosting, and reduce motor-side electromagnetic interference. Sensorless control of CSI-fed permanent magnet synchronous machines (PMSMs) remains less mature than VSI counterparts, primarily because conventional implementations require measurement of all
circuit state variables. This paper proposes a weak-resonance-based approximation that reconstructs stator currents from inverter modulation commands and feedforward capacitor-current estimation, thereby reducing the sensing requirement to the dc-link current and two terminal voltages. The proposed observer–PLL structure is analysed for computational complexity and validated through simulations and experiments on a 100~W, 100~krpm GaN-based two-stage CSI prototype (buck + CSI). Quantitative results demonstrate accurate rotor-position tracking and high-bandwidth operation while maintaining the reduced sensor set. Proposed method performs well in simulation and experiment, achieving a position estimation error below $5^\circ$ at 100~krpm.
Read the full abstract ▾
All authors Nail Tosun, Devinda Molligoda, Xu Deng, Barrie Mecrow
Machine Learning
Evaluating the Effectiveness of SechKAN on 1D Data
Hoang-Thang Ta
The connection between the Kolmogorov-Arnold representation
theorem (KART) and neural network design has led to the development of Kolmogorov-Arnold Networks (KANs), with applications ranging from STEM problems to AI tasks. In this paper, we investigate the effectiveness of a KAN variant, SechKAN, which relies on
hyperbolic secant (sech) functions as basis functions, with a 1D projection to reduce the number of parameters to a level comparable to MLPs. We evaluate SechKAN on three 1D classification
datasets: UCI Human Activity Recognition (UCI HAR), ElectricDevices, and Crop, and compare it with several effective networks, including EfficientKAN, MLP, CNN1D, ResNet1D, and DSCNN1D, using approximately comparable parameter budgets. The results indicate that SechKAN achieves competitive performance across the three
datasets, with particularly strong performance on Crop. Ablation studies further show that grid size and normalization affect performance, suggesting that SechKAN's effectiveness depends on the
dataset and architectural choices. Our source code and experimental implementation are publicly available at: https://github.com/hoangthangta/SechKAN_1D.
Read the full abstract ▾
Machine Learning
Neural Approximation by Function Composition: Rigidity and Doubly Exponential Convergence
Wentao Huang and Haizhang Zhang
Deep neural networks approximate functions by composing affine maps with nonlinear activations, but how composition itself creates approximation power is not yet fully understood. We investigate a fundamental mechanism: geometrically weighted sums of iterates of a single scalar generator function. This mechanism underpins the classical tent-map construction of the function \(x - x^2\) and related recursive representations used by Yarotsky, W. E, et al., to analyze the approximation powers of deep neural networks. First, we establish a
rigidity theorem: for continuous piecewise linear generators with a finite number of segments, any \(C^3\) function that can be represented in this way is at most quadratic. For non-affine quadratic functions, the
geometric factor is at least $1/4$. This result both reveals limitations of the tent-map approach and complements existing methods based on hierarchical bases and recursive
polynomial constructions. Second, using an exact remainder identity as guidance, we construct a smooth generator whose iterates yield doubly exponential error decay in total depth for square approximation and, through multiplication modules, for each fixed
polynomial. For power series with absolutely summable coefficients on \([-1,1]^d\), distributing depth according to monomial degree yields a uniform approximation error of order \(O(e^{-cL^{1/d}})\) on each interior cube. These findings demonstrate how generator dynamics and remainder estimates govern depth allocation and approximation rates of deep neural networks.
Read the full abstract ▾
Artificial Intelligence
AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing
Yijia Hao, Pratibha Verma, Dongxu Guo et al. (+4 more)
Analog
circuit sizing remains a challenging and time-consuming task due to the large design space, strong performance trade-offs, and increasing
circuit complexity in scaled technologies. Although recent large
language model (LLM)-based methods show promise in improving sample efficiency and interpretability, existing approaches often lack explicit
circuit-
topology understanding and are mainly evaluated on relatively simple analog building blocks. This paper presents a multi-
agent LLM-based framework for complex analog
circuit sizing. The proposed framework first analyzes the
circuit topology and decomposes the netlist into functional blocks and substructures. It also extracts lightweight design knowledge for reuse. Based on the extracted
topology and knowledge, a planner coordinates multiple role-specialized sizing
agents to update design variables and achieve global performance specifications. This workflow mimics the collaborative process of an expert analog design team and provides a structured, interpretable, and simulation-driven optimization procedure. The framework was validated on eight
circuits, with the largest design containing up to 55 transistors and 60 sizing variables. Notably, for the LDO
benchmark, the proposed method achieved a 60% success rate with an average of 83 iterations, where classical optimizers failed to find feasible solutions. Further, ablation studies demonstrate that
topology understanding, design-knowledge infusion, and
agent specialization provide complementary benefits. The source code is available to support reproducibility.
Read the full abstract ▾
All authors Yijia Hao, Pratibha Verma, Dongxu Guo, Cristian Sestito, Michael O'Boyle, Christos-Savvas Bouganis, Themis Prodromakis
Hardware Architecture
Decoupling Logical Masks from GPU Execution for Dynamic Block-Sparse Attention
Shanghao Liu, Xiaoyun Yu, Wanting Li et al. (+1 more)
Attention computation makes inference expensive in
video diffusion transformers (vDiTs), which generate
videos through iterative denoising. Block-sparse
attention (BSA) reduces this cost by computing only blocks selected by a logical mask, which specifies
attention interactions to compute. However, coupling logical block geometry to execution choices limits adaptation to varying masks and graphics processing units (GPUs), while runtime kernel specialization can incur preparation overhead that outweighs execution time savings. We present Tessera, a specialized runtime for dynamic BSA that decouples logical masks from GPU execution while preserving specified
attention interactions. Its physical mapping layer retains, combines, or subdivides logical
attention blocks into physical tiles suited to different
attention mask shapes and GPU architectures. Its task organization layer groups and schedules tiles within GPU tasks to reuse data, expose parallelism, and overlap data movement with computation. Finally, profile-guided regime selection enables low- overhead execution plan selection through a lookup table constructed from offline profiling. We implement Tessera with specialized CUDA kernels supporting four NVIDIA GPU generations. Evaluated on 2,315 real
attention masks and industrial
video diffusion models, Tessera achieves up to 6.79x BSA request speedup over baseline systems in the evaluated
video diffusion models.
Read the full abstract ▾
All authors Shanghao Liu, Xiaoyun Yu, Wanting Li, Wenqi Jiang
Multimedia
TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum
Xinyue Guo, Jianxuan Yang, Daiguo Zhou et al. (+4 more)
Visual object removal can eliminate a target from
video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual inconsistency. Existing
video inpainting models operate solely on pixels, while audio editing models, especially for the sound removal task, are typically driven by text and therefore rely on limited single-modal control, which is less effective than
multimodal guidance that provides stronger semantic grounding and temporal synchronization cues. In this paper, we present Text-Visual Guided Sound Removal (TV-AudioRemover), a target sound removal framework that leverages the visually edited
video together with a natural-
language instruction to suppress the sound associated with the removed visual object from the original audio mixture. To acquire high-quality training data, we devise a pipeline to construct a million-scale
dataset of single-object audio-visual aligned samples, from which we synthesize mixture-target pairs customized for model training. To effectively leverage visual context and follow instruction intent, we augment the model architecture with task
tokens, generalizable instruction modeling, and modality-specific global guidance. We further adopt multi-task training to strengthen task-role comprehension, and employ a hard-mixture curriculum that leverages semantically similar acoustic mixtures during fine-tuning to enhance fine-grained source discrimination. To support evaluation, we present AV-Remove-Bench, a comprehensive audio-visual object removal
benchmark, along with dedicated objective metrics and an MLLM-based evaluation protocol. Experiments demonstrate that our method achieves state-of-the-art performance on both subjective and objective metrics. Project page: https://yjx-research.github.io/TV-AudioRemover/.
Read the full abstract ▾
All authors Xinyue Guo, Jianxuan Yang, Daiguo Zhou, Jiagao Hu, Yuxuan Chen, Fei Wang, Jian Luan
Computation and Language
Isolated Sign Language Recognition for Icelandic Sign Language: Experiments in a Low-resource Setting
Finnur Ágúst Ingimundarson, Gu{\dh}ný Björk {\TH}orvaldsdóttir, Mathias Müller et al. (+1 more)
We present the first experiments on isolated sign
language recognition (ISLR) for Icelandic Sign
Language (ÍTM). We use ÍTM SignWiki, a
dataset derived from a bilingual Icelandic–ÍTM online dictionary. It is genuinely low-resource: 1,845
videos cover 849 classes, 86% of which have only two examples, making the full task effectively one-shot recognition across signers. We compare two open-source ISLR frameworks, OpenHands and SPOTER, on three tasks of increasing vocabulary size (22, 117 and 849 classes), and evaluate three pose
estimators and two forms of cross-lingual transfer. With ÍTM data alone, SPOTER outperforms OpenHands on all three tasks, and MediaPipe poses give better results than AlphaPose or SDPose. Cross-lingual transfer brings the largest gains: pretraining SPOTER on American Sign
Language data before finetuning on ÍTM raises accuracy by 14–24 percentage points, to 72.7%, 47.9% and 22.6% on the three tasks, and
multilingual training with data from six other sign
languages lifts OpenHands from 1.41% to 28.86% on the full task. Although far from practical use, the results suggest that transfer from better-resourced sign
languages is promising for very low-resource ones. We release our adapted versions of both frameworks.
Read the full abstract ▾
All authors Finnur Ágúst Ingimundarson, Gu{\dh}ný Björk {\TH}orvaldsdóttir, Mathias Müller, Sarah Ebling
Computer Vision
MatchFusion: Explicit-Implicit Instance Matching for Spatio-Temporal Multimodal Autonomous Driving
Xiaoyu Li, Jiajia Fu, Long Shi et al. (+7 more)
Sparse instance representations provide a compact interface for spatial
LiDAR-camera and temporal past-current interaction in
multimodal perception and E2EAD. Effective interaction requires reliable instance correspondences despite
geometric discrepancies and heterogeneous semantic representations.
Attention-based methods exploit contextual semantics but often require specialized representation
alignment, increasing computational overhead. In contrast, association based on structured object states is efficient and interpretable but lacks contextual evidence to resolve ambiguous matches. To combine these complementary strengths, we propose MatchFusion, a learnable instance matching and fusion module for spatio-temporal
multimodal autonomous driving. MatchFusion initializes pairwise affinities using
geometric similarity and category consistency, then selectively refines structurally plausible associations using instance
embeddings. The resulting soft matchmap guides a common residual aggregation operator for adaptive information exchange. This unified matching-fusion formulation supports spatial
LiDAR-camera and temporal past-current interaction, using multi-view image-plane geometry and motion-compensated BEV geometry as the respective structural priors. Experiments on nuScenes demonstrate consistent perception gains across diverse front-end configurations. Compared with a prior instance-centric fusion method, the MatchFusion-equipped system achieves higher perception accuracy while reducing FLOPs by 55.3% and GPU
memory usage by 39.3%, with the matching-fusion module accounting for only 3.7% of total perception latency. Integrating temporal MatchFusion into SparseDrive further improves perception within an E2E framework without additional supervision. These results establish explicit-implicit matching as an effective and efficient mechanism for spatio-temporal instance interaction.
Read the full abstract ▾
All authors Xiaoyu Li, Jiajia Fu, Long Shi, Tianyu Du, Ruihang Li, Xian Wu, Lijun Zhao, Yingtao Zhang, Lining Sun, Ruifeng Li
Computation and Language
BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval
Samuele Garda and Ulf Leser
Biomedical Entity Linking disambiguates mentions to entities in a knowledge base (KB), making it the cornerstone of information extraction pipelines. While
embedding-based models are a popular approach for the task, they suffer from a key limitation. They compress mentions (and entities) into a single vector, forcing the model to average away crucial fine-grained differences. We present BELXTR, a novel
embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage
token-level matching information. BELXTR extends the original XTR model to biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion. Experiments across ten corpora and five KBs show that BELXTR improves upon current state-of-the-art in half of the corpora with an average improvement of 5pp recall@1. The largest gains are reported on the challenging cross-species gene disambiguation subtask, where BELXTR outperforms an LLM-powered retrieve-and-rerank pipeline and closely approaches a specialized rule-based system. Our results highlight multi-vector models as a practical alternative to hard-to-maintain rule-based systems or in scenarios where LLM-based reranking is too costly as in PubMed-scale mining. The code to reproduce our experiments can be found at: https://github.com/sg-wbi/belxtr.
Read the full abstract ▾
Numerical Analysis
The inverse elastic scattering problem in the cavity with impedance boundary
Shiyu Xu, Huiling Zheng and Fang Zeng
In this paper, we investigate the elastic inverse scattering problem in a two-dimensional cavity with an impedance boundary condition. We prove that the scattered fields inside the cavity satisfy a reciprocity relation, and prove that both the shape of cavity and the impedance parameter on the boundary can be uniquely determined from the scattered fields measured on an interior curve. Numerically, we first employ the linear sampling method to reconstruct the shape, and then recover the impedance parameter by combining potential theory with the least squares method. Several numerical experiments are presented to demonstrate the feasibility and effectiveness of our methods.
Read the full abstract ▾
Software Engineering
Confidence-Guided Cross-Modal Knowledge Transfer for Multimodal Anomaly Detection in Microservice Systems
Peipeng Wang, Xiuguo Zhang, Lihua Zhang et al. (+3 more)
Accurate anomaly detection is essential for reliable and secure operations of microservice systems. While an increasing number of studies have shifted from unimodal modeling to
multimodal interaction and fusion, effectively leveraging reliable cross-modal information remains challenging. The challenge primarily stems from two aspects. Firstly, different modalities are influenced by factors like load fluctuations, leading to dynamically changing reliability. Secondly,
multimodal data exhibit heterogeneity in both structure and semantics. Therefore, we propose a confidence-guided Cross-Modal knowledge Transfer method for
multimodal Anomaly Detection (CMT-AD). It jointly models metrics and logs within a unified deep clustering framework and estimates modality reliability through the soft clustering distributions, where clustering uncertainty is quantified into confidence scores. Guided by these confidence scores, the model actively analyzes the contributions of each modality in cross-modal interactions and supplements low-confidence modalities with knowledge from high-confidence ones. To further mitigate cross-modal heterogeneity, we introduce a gated intermediate modality and design structural and semantic consistency constraints that align the original modalities with the intermediate modality to preserve similarity structures and semantic distributions across modalities. Furthermore, intra-modal and cross-modal regularization terms are incorporated to enhance cluster compactness and mitigate negative transfer. We evaluated CMT-AD on three large-scale
datasets, and the results demonstrate that CMT-AD outperforms state-of-the-art approaches and achieves an F1-score higher than 0.9.
Read the full abstract ▾
All authors Peipeng Wang, Xiuguo Zhang, Lihua Zhang, Zhiying Cao, Jingchun Zhou, Zheng Li
Numerical Analysis
A Multirate Transient Simulation Technique for Circuits described by Integro-Differential Equations
Hans Georg Brachtendorf and Kai Bittner
The multirate partial differential equation (PDE) technique is considered as one of the most powerful methods for the simulation of
radio frequency (RF)
circuits. The method reformulates the underlying ordinary differential algebraic equation (DAE) by a PDE. The DAE solution is obtained along a characteristic curve of the PDE. Numerical solution techniques comprise (envelope modulated) Harmonic Balance (HB), multistep finite difference (FD) and spline/wavelet techniques. All techniques have disadvantages when mixed lumped/distributed devices occur and the waveforms exhibit pulse shaped behavior. Furthermore, communication systems are modeled and simulated by the Equivalent Complex Baseband (ECB) approach. Signals and impulse responses are described by their baseband counterparts, employing the
Hilbert transformation. A coupled system/
circuit simulation requires therefore novel numerical techniques for the solution of integro-differential equations.
Read the full abstract ▾
Computation and Language
MemoryAthena: Adaptive Routing over Latent and Generated Memories
Mingyuan Li, Guangsheng Yu, Juyuan Zhang et al. (+4 more)
Learned-
memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whether useful
memory can also be generated rather than only retrieved. MemoryAthena uses three pathways: direct Engram
retrieval (E), generation from retrieved Engram cues (GE), and generation from causal backbone states without consulting the
memory table (GH). Generated
memory is conditionally useful: it can complement E in one context but interfere with it in another. MemoryAthena therefore treats E as an anchor and learns when a generated representation should intervene. With the backbone,
memory, generators, and readers frozen, a lightweight causal routing head is trained from counterfactual future-
token likelihood advantages of GE and GH relative to E. At inference time, an admitted candidate modifies the E residual through bounded interpolation, while rejection recovers the direct pathway exactly. On question answering, MemoryAthena raises the five-task average from 37.65 to 39.28 over the direct pathway of the same checkpoint, while the six-task general-NLP average increases from 76.73 to 79.13. The complete
memory-side system contains approximately 201M parameters, excluding the frozen backbone. Further analyses show complementary strengths among E, GE, and GH across tasks and inputs. These results support generated
memory as a selective correction to direct
retrieval and highlight routing when, which, and how strongly to intervene as the central challenge.
Read the full abstract ▾
All authors Mingyuan Li, Guangsheng Yu, Juyuan Zhang, Xu Wang, Zhibo Man, Haonan Zhang, Shaoxiong Ji
Artificial Intelligence
When Clinical Judgment Becomes a Predictive Shortcut: Two Questions Clinical AI Must Answer Before Deployment
Jing Yang, Long R. Jiao, Zongjiu Zhang et al. (+1 more)
Clinical AI can predict outcomes using information generated by existing clinical judgment. Such performance alone cannot establish usefulness before recognition or across care processes. We propose evidence requirements matched to intended use and information conditions, with additional state-reference and proxy-relative timing tests for stronger recognition claims. This framework helps hospitals assess whether the conditions supporting performance hold when assistance is most needed. These questions remain outside current evaluation practice leakage checks, overall predictive performance, and external validation do not address them; the framework makes them explicit and specifies the direct evidence required to answer them.
Read the full abstract ▾
All authors Jing Yang, Long R. Jiao, Zongjiu Zhang, Xiujun Cai
Computer Vision
Less Is More in the Long Tail: Stage-Adaptive Sample Selection for Annotation-Efficient Dense Prediction
Xiaofei Du, Lei Zhang, Shuyu Yan et al. (+2 more)
Deep learning performance generally improves with increasing training data, yet this scaling is fundamentally constrained by annotation cost in large-scale dense prediction tasks with long-tailed category distributions, where pixel- or voxel-level annotation is prohibitively expensive. We propose SASS (Stage-Adaptive Sample Selection), a stage-adaptive data-selection framework for pool-based active learning in long-tailed dense prediction. SASS combines three components: label-free self-supervised gradient scoring, prior-guided category rebalancing with validation-driven feedback, and stage-adaptive acquisition aligned with model training dynamics. This design avoids candidate ground-truth masks during gradient scoring while making acquisition responsive to long-tail imbalance and evolving representations. We evaluate SASS on a
multimodal 3D medical
segmentation testbed comprising over 100,000 samples spanning 108 anatomical structures. SASS recovers 98.3% of full-
dataset performance with a 40% training-pool annotation budget, outperforming BADGE by 5.1 percentage points. Moreover, SASS exhibits a statistically supported less-is-more pattern, surpassing full-
dataset training at the Hard-group level and, at the structure level, for the pancreas and gallbladder. More broadly, SASS shows that annotation-efficient learning depends not only on which samples are selected, but also on how the annotation budget is distributed across categories and when model-derived scores begin to guide selection.
Read the full abstract ▾
All authors Xiaofei Du, Lei Zhang, Shuyu Yan, Manning Wang, Zhijian Song
Artificial Intelligence
Optimizing the Score, Losing Sight of the Task: Reward Hacking Across Weights, Selection, and Prompts
Vansh Wahi
A higher evaluation score does not always mean a better
language model system. When optimization exploits an evaluator's mistakes, measured progress can conceal unchanged or deteriorating task performance. This failure can arise through parameter updates, selection among generated outputs, or revisions to persistent
prompts. We develop a comparative framework for reward hacking across these three optimization substrates: weights, selection, and text. Building on the Proxy Compression Hypothesis and research on inference-time and in-context reward hacking, we examine how reachable behavior, optimization budgets, and persistent adaptation shape exposure to proxy error. We formalize a distance-dependent upper bound on evaluator disagreement and a capacity ordering for nested policy classes, then show why distance alone cannot establish a universal ranking of vulnerability. An exact finite-output illustration demonstrates how the location of a scoring defect changes the behavior favored by each method. We also map representative defenses across substrates, identifying which mechanisms transfer directly and which offer only functional analogies. Persistent
prompts receive particular
attention: their contents are inspectable, but the behavior induced by a small textual change may be difficult to anticipate. The formal analysis, numerical illustration, and published evidence together provide a basis for comparing optimization methods and identifying the conditions under which their defenses transfer. The resulting framework connects optimization choices to verification requirements: reliable improvement depends on controlling accessible failure modes and preserving evidence of task quality independent of the score being optimized.
Read the full abstract ▾
Computer Vision
Visual Jev: Accurate and Efficient Decisions from Shared Visual Context
Guanxu Yu and Yuhang Yao
Many
vision applications ask several independent, forced-choice questions about the same image. Visual Jev encodes the image and public context once, executes isolated question suffixes as a batch, and reads candidate probabilities from the backbone's
language-model head. Across four
benchmarks, answer-supervised post-training raises equal-weight macro accuracy from 70.6% to 76.1%, with the gain concentrated on the two task families represented in training. At N=32 questions per image, shared batched execution is 8.9x faster in warm amortized time than independent serial execution and remains 3.4x faster than an already-batched baseline that recomputes the prefix, at the cost of higher peak
memory. A matched typed-head control offers no consistent accuracy advantage over the
language-model-head readout. The supported design is therefore simple: adapt the backbone for quality, retain the existing readout, and share execution for efficiency.
Read the full abstract ▾
Computer Vision
Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes
Yuling Xi, Haokai Zhang, Muzhi Zhu et al. (+10 more)
Metric
reasoning is a critical and challenging task for
Vision Language Models (VLMs), playing a pivotal role in
embodied AI tasks such as robotic manipulation and autonomous
navigation. However, current spatial
reasoning remains bottlenecked by rigid pixel-level supervision; such localized optimization often compromises general
multimodal intelligence, triggering performance degradation or catastrophic forgetting of broad
reasoning capabilities. To address these limitations, we introduce Metric-Bench, a focused
benchmark designed to guide metric-spatial
reasoning using contextual information. By incorporating in-image reference objects with known physical dimensions, Metric-Bench guides models to implicitly learn the 2D-to-3D mapping without camera intrinsics. We further present MetricReasoner, a task-adapted reinforcement fine-tuning recipe for reference-grounded metric
reasoning, using structured
prompts and verifiable numerical rewards. Extensive experiments on Metric-Bench demonstrate that our approach significantly enhances spatial metric understanding, outperforming existing and even larger proprietary models by 43.1%, while improving downstream
embodied performance over a spatial-specialized counterpart by 30.4% on RoboSpatial overall accuracy and 9.3% on ERQA, and additionally delivering consistent gains on general
benchmarks (15.9% on V$\star$Bench, 88.9% on BLINK), indicating that the proposed adaptation does not necessarily compromise general VLM capabilities.
Read the full abstract ▾
All authors Yuling Xi, Haokai Zhang, Muzhi Zhu, Hao Zhong, Zongze Du, Hengyu Zhao, Chenchen Jing, Yufei Yin, Bin Qin, Yongjie Yang, Zhenbo Luo, Hao Chen, Chunhua Shen
Machine Learning
Gaussian Flow-Matching Schedules: Implications for Sampling and Training
Arsène Claustre, Hugo Negrel, Claire Boyer et al. (+2 more)
Flow-matching schedules affect both sampling dynamics and the variance of the regression target. For centered commuting Gaussians, we show that a direction-dependent schedule decomposes into two independent design choices: a variance path, which fully determines the intermediate laws and probability flow, and a factorization, which leaves this flow unchanged while controlling irreducible regression variance. On the sampling side, we analyze finite-step Euler accuracy and derive a necessary drift bound for exact N -step sampling, connecting the geodesic and the logarithmic path. On the training side, for any fixed path, we derive closed-form factorizations that either minimize time-averaged regression variance or make it constant along the path.
Read the full abstract ▾
All authors Arsène Claustre, Hugo Negrel, Claire Boyer, Kimia Nadjahi, Eric Vanden-Eijnden
Computer Vision
Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features
Milad Mirjalili, Enrique Alegre Gutiérrez, Eduardo Fidalgo Fernández et al. (+3 more)
This work presents a
video summarization
algorithm based on multi-object tracking and person reidentification. We integrate facial
embeddings, 3D body-shape features, and visual appearance into a unified tracking framework. These representations enable hierarchical identity assignment and tracking through bidirectional anchoring, which robustly recovers trajectories under severe occlusion or low visual quality. From these stable trajectories, we generate a compact set of summaries for each identity. We select keyframes using a multi-factor weighting scheme that optimizes biometric clarity, social interaction, and motion dynamics, while Adaptive Non-Maximum Suppression ensures temporal diversity. Evaluation on a custom
dataset demonstrates tracking stability, achieving an IDF1 of 97.89% and a MOTA of 95.79%. Compared to Top-K selection, our
algorithm also increases visual diversity by 146%, temporal coverage by 89%, and information retrievability by 3.5%.
Read the full abstract ▾
All authors Milad Mirjalili, Enrique Alegre Gutiérrez, Eduardo Fidalgo Fernández, Víctor González Castro, Rocío Alaiz Rodríguez, Manuel Castejón Limas
Machine Learning
In-Context Guidance: Learning Inter-Task Synergies via Numerical Foundational Models for Few-Shot Multitask Optimization
Tingyang Wei, Haofeng Wu, Jiao Liu et al. (+3 more)
Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation under limited evaluation budgets, leading to negative transfer. This paper introduces In-Context Guidance Multitask Optimization (ICG-MTO), a novel framework that leverages numerical foundational models to improve inter-task coupling estimation in few-shot scenarios. Unlike conventional methods that rely solely on scarce observed data, ICG-MTO employs a frozen foundational model to infer auxiliary guidance through in-context learning. The framework operates through three stages: constructing an
algorithm-specific in-context query from evaluated solutions, using the foundational model to infer a guidance signal characterizing predictive relationships among tasks, and translating this signal into
algorithm-specific guidance for maximum-a-posteriori coupling estimation. This approach provides regularization during the early, data-scarce stages of optimization and gradually relinquishes control as task-specific observations accumulate. We instantiate the framework in multitask
Bayesian optimization as ICG-MTBO, using directional fitness-class queries to guide inter-task coupling estimation, and further instantiate it in MFEA-II using decision-space-overlap queries to guide random mating probability estimation. Experiments across synthetic
benchmarks and a real-world
robot arm control problem, together with evaluations under different acquisition functions and evolutionary multitasking, demonstrate the effectiveness and generality of ICG-MTO for few-shot multitask optimization.
Read the full abstract ▾
All authors Tingyang Wei, Haofeng Wu, Jiao Liu, Zhao Wei, Puay Siew Tan, Yew-Soon Ong