arXiv:2605.12827v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) deployed as cloud services can be stolen through model-extraction attacks, which train a surrogate from query responses to reproduce the target’s behavior, and a growing line of ownership defenses tries to prevent or trace such theft. This paper asks two questions: how hard is it to […]
Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training
arXiv:2605.26189v1 Announce Type: cross Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible to standard training metrics. We present a systematic study of HiF8 W8A8 QAT for OpenPangu-Embedded-1B through the lens of Delayed Tensor Scaling (DTS). Across eight controlled experiments, we identify and disentangle two orthogonal […]
PHALAR: Phasors for Learned Musical Audio Representations
arXiv:2605.03929v4 Announce Type: replace-cross Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to $approx 70%$ over the state-of-the-art while requiring $<50%$ of the parameters […]
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
arXiv:2605.26193v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) has long been a hot research topic in data mining due to its various applications. Recent studies challenge the effectiveness of popular deep learning methods for TSAD, suggesting their failure in detecting subtle and prolonged anomalies. Outlier Exposure (OE) and Masked Autoencoder (MAE) emerge as […]
Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering
arXiv:2605.24297v2 Announce Type: replace-cross Abstract: Two questions regarding practitioners’ use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other landscapes? By evaluating 22 pre-trained embedding models (ranging from 22M to 12B parameters) on three tasks — information […]
From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework for Legal Indicator Computation
arXiv:2605.26926v1 Announce Type: new Abstract: Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the complexity, scale, and interpretive nature of legal language, as well as the variability in available document quality. Existing natural language processing techniques and generative models can assist […]
Beyond Transfer Accuracy: Faithful Circuits for Controlled Low-Resource Adaptation
arXiv:2601.08146v3 Announce Type: replace-cross Abstract: Existing circuit discovery methods rely on templated tasks with clean counterfactuals, limiting their use on diverse natural text. We adapt Contextual Decomposition for Transformers (CD-T) for unstructured settings via label-balanced activation means and task-directional relevance scoring, enabling counterfactual-free circuit discovery. We leverage these circuits for Circuit-Targeted Supervised Fine-Tuning (CT-SFT), restricting […]
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)
arXiv:2605.26942v1 Announce Type: new Abstract: LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper presents a hybrid verification architecture combining formal symbolic methods with neural semantic analysis to provide complementary guarantees for LLM-generated content. This architecture employs […]
LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction
arXiv:2603.12647v3 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and […]
Generating Robust Portfolios of Optimization Models using Large Language Models
arXiv:2605.27013v1 Announce Type: new Abstract: Mathematical optimization is a powerful tool for structured decision-making across domains such as resource allocation and planning. Formulating optimization models faithful to reality, though, remains a significant bottleneck as it typically demands both domain expertise and optimization knowledge that are often scarce. Recent advances in large language models (LLMs) promise […]
Contextual Role Modulates Object Representational Geometry in the Human Brain
arXiv:2605.23111v2 Announce Type: replace Abstract: The human brain represents objects in a way that is both invariant across instances and flexible enough to support different contexts and tasks. Yet it remains unknown how object representations are dynamically remapped as the same object shifts across contextual roles. Here we combined fMRI with naturalistic movie viewing to […]
Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
arXiv:2605.27023v1 Announce Type: new Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are often very incomplete. To perform zero-shot knowledge graph completion in unseen KGs, which have different relational vocabularies from those used for pre-training, KG foundation models […]