AI News

DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration (arxiv.org)

A Flatness-Generalization Relation in the Teacher-Student Tree-Committee Machine (arxiv.org)

SAGE: A sampling-aware global evaluation benchmark for species distribution modeling (arxiv.org)

Ensembles of Exactly Solved Subsamples for Clusterwise Regression: Trimming Without a Trimming Level (arxiv.org)

Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change (arxiv.org)

TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise (arxiv.org)

Design-Ignoring versus Design-Respecting World Models for Epidemiology (arxiv.org)

Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation (arxiv.org)

Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations (arxiv.org)

Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks (arxiv.org)

High-dimensional Gaussian Graphical Model Testing for Long-Memory Time Series (arxiv.org)

Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding (arxiv.org)

Learning to Bias: Machine Learning-Enhanced Particle Filters (arxiv.org)

Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs (arxiv.org)

An End-to-End Pipeline for Causal ML with Continuous Treatments: An Application to Financial Decision Making (arxiv.org)

Cost-Aware Best-LLM Identification using Dueling Feedback (arxiv.org)

Strategic Self-Consistency (arxiv.org)

First-Order Stationarity of Reverse Diffusions (arxiv.org)

Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach (arxiv.org)

Geometric Feature Learning for Functional Data Valued on the Symmetric Positive Definite Manifold (arxiv.org)

Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers (arxiv.org)

Equation discovery with Bayesian tree-adjoining grammars (arxiv.org)

Geometric Moment Contraction for Stochastic Nesterov Acceleration (arxiv.org)

Conformal Prediction under Exponential-Tilt Joint Shift (arxiv.org)

MARCEDES: Score-based causal discovery under non-Gaussianity with continuous optimization (arxiv.org)

Ordinary Nonconvex SGD under Distance-Dependent Moments: Finite-Horizon Stationarity and Nagaev Bounds (arxiv.org)

Bayesian Uncertainty Quantification for fMRI Functional Connectivity via Simulation-Based Inference (arxiv.org)

Adaptive multi-resolution Gaussian processes: Scalable exact inference with naturally data-sparse covariance matrices (arxiv.org)

Low-Rank Friction for Memory-Efficient Transformer Pretraining (arxiv.org)

Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport (arxiv.org)

Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers (arxiv.org)

Distribution of hitting times for dissipative random dynamical systems on $\mathbb{R}^d$, with application to stochastic gradient descent (arxiv.org)

Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence (arxiv.org)

Agentic Limit Order Books: Phase Transitions and Market Impact (arxiv.org)

Anatomy-Aware Dexterity-Driven Design Optimization of Surgical Continuum Robots (arxiv.org)

JevSoup: System-One Routing for Training-Free LoRA Composition (arxiv.org)

What Improves Multimodal Misinformation Detection? Answers from a Large-Scale Empirical Study (arxiv.org)

DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education (arxiv.org)

HuPER: A Human-Inspired Framework for Phonetic Perception (arxiv.org)

AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side (arxiv.org)

SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations (arxiv.org)

Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods (arxiv.org)

NORTHMARK DATA CENTER + SPARTANBURG WATER: WATER CAPACITY & WATER ... (www.facebook.com)

Thinking fast and slow in AI: The role of metacognition (2021) (arxiv.org)

20 Agentic Use Cases of TypeSafe AI’s Jev (www.marktechpost.com)

Google Research Introduces an AI Video Co-Director: 4 Agentic Frameworks for Coherent, Minutes-Long Video Generation (www.marktechpost.com)

Nissan's third generation e-POWER powertrain (www.nissan-global.com)

Congress questions data centre push in Maharashtra - The Tribune (www.tribuneindia.com)

Owed a billion dollars in Nvidia stock (colo.to)

Behold the pawpaw (www.cbc.ca)