1-Lipschitz Neural Networks on Hadamard Manifolds
arXiv:2607.19335v1 Announce Type: cross Abstract: Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strategies…
Papers 5629 stories
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
arXiv:2607.18290v1 Announce Type: new Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks,…
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
arXiv:2606.16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative…
Fast data inversion for high-dimensional Ornstein-Uhlenbeck processes from noisy measurements
arXiv:2501.01324v5 Announce Type: replace-cross Abstract: In this work, we develop a scalable approach for a flexible latent factor model for high-dimensional dynamical systems. Each latent factor…
AI Tool Discovery at Scale: All You Need is DNS
arXiv:2607.18242v1 Announce Type: new Abstract: The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of tools, yet existing solutions buckle…
Dice Loss for Data-imbalanced NLP Tasks
arXiv:1911.02855v4 Announce Type: replace Abstract: Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly…
The Story Shapes the Agent: Narrative Priors in LLM Behavior
arXiv:2607.18566v1 Announce Type: new Abstract: Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than…
Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
arXiv:2607.18508v1 Announce Type: new Abstract: Preference over model-generated emotion descriptions is emerging as a standard evaluation metric for multimodal emotion understanding, exemplified by the MER2026 MER-Prefer…
Hierarchical Physics-Embedded Learning for Partially Known Spatiotemporal Dynamics
arXiv:2510.25306v3 Announce Type: replace Abstract: Partial physical knowledge--governing structures known, constitutive relations or their combinations not--pervades spatiotemporal systems. Existing scientific machine learning paradigms learn evolution largely…
Boundary-Adapted PINNs for Elliptic Dirichlet Problems: $H^2(Omega)$ A Priori Error Bounds with Application to Mean Escape Time Computation
arXiv:2607.19167v1 Announce Type: cross Abstract: Motivated by the numerical computation of the Mean Escape Time (MET) $tau:Omegatomathbb{R}$ of a stochastic process from a bounded domain $Omegasubseteqmathbb{R}^d$,…
Cheap Permutation Testing
arXiv:2502.07672v3 Announce Type: replace-cross Abstract: Permutation tests are a popular choice for distinguishing distributions and testing independence, due to their exact, finite-sample control of false positives…
On the sensitivity of machine-learned probabilistic weather forecast models to scale-aware scoring rules
arXiv:2607.19161v1 Announce Type: cross Abstract: Probabilistic forecast models can be machine-learned from data using loss functions based on scoring rules such as the Continuous Ranked Probability…
BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data
arXiv:2607.18241v1 Announce Type: new Abstract: Large language models (LLMs) excel at analyzing individual documents but break down on exhaustive, cross-entity analytical questions over enterprise-scale datasets due…
Evaluating Style-Personalized Text Generation: Challenges and Directions
arXiv:2508.06374v3 Announce Type: replace Abstract: With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--"write like me"--has become…
Epistemic Familiarity is Associated With Belief Stability in Large Language Models
arXiv:2511.19166v4 Announce Type: replace Abstract: Large language models (LLMs) are widely used as information sources, yet small changes in semantic assumptions can destabilize their beliefs. We…
ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization
arXiv:2607.18466v1 Announce Type: new Abstract: Recent advances in differentiable Gaussian splatting have highlighted the potential of primitive-based approaches as alternative scene representations for interactive, high-quality, volume…
Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
arXiv:2607.18554v1 Announce Type: cross Abstract: We develop the Continuous Distributed Coupled Policy Gradient (CDCPG) algorithm for cooperative reinforcement learning in networked Markov decision processes with continuous…
Dual-domain fused LSTM modeling for efficient time-dependent reliability analysis
arXiv:2607.18291v1 Announce Type: new Abstract: Time-dependent reliability analysis is crucial for ensuring the long-term safety and performance of engineering systems under uncertainties. However, traditional surrogate model…
Using binary silver labels in electronic health records-based computable phenotyping algorithms
arXiv:2607.18431v1 Announce Type: cross Abstract: Gold-standard phenotype labels are often unavailable at scale in electronic health record (EHR) studies because they require manual chart review. Weakly…
Data Reliability Scoring
arXiv:2510.17085v2 Announce Type: replace-cross Abstract: How can we assess the reliability of a dataset without access to ground truth? We introduce the problem of reliability scoring…
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
arXiv:2510.02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified…
PathReportEval: A Systematic Benchmark for Pathology Report Generation
arXiv:2607.18448v1 Announce Type: new Abstract: Pathology report generation from whole-slide images (WSIs) is a rapidly growing multimodal learning problem, yet progress is difficult to measure because…
For What Reason? Interpreting Models' Encoding of Causation and Antithesis
arXiv:2607.18570v1 Announce Type: new Abstract: Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality. In this work, we investigate…
Surprise Forcing: What to Remember, When to Skip in Long Video Generation
arXiv:2607.18436v1 Announce Type: new Abstract: Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly across a…