AI News

EpiBench: Verifiable Evaluation of AI Agents on Epigenomics Analysis (arxiv.org)

Optimal Spatio-Temporal Decoupling for Bayesian Conformal Prediction (arxiv.org)

GEMSS: A Variational Bayesian Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems (arxiv.org)

Entropic Mirror Monte Carlo (arxiv.org)

Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design (arxiv.org)

Real-Time Execution with Autoregressive Policies (arxiv.org)

Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression (arxiv.org)

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential (arxiv.org)

From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints (arxiv.org)

Quasi-Bayes empirical Bayes: a sequential approach to the Poisson compound decision problem (arxiv.org)

Plug-and-Play image restoration with Stochastic deNOising REgularization (arxiv.org)

Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination (arxiv.org)

Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability (arxiv.org)

Computationally tractable robust differentially private mean estimation (arxiv.org)

Valid Inference with Synthetic Data via Task Exchangeability (arxiv.org)

Learning with Simulators: No Regret in a Computationally Bounded World (arxiv.org)

Symmetry-electronic fingerprints reveal competing magnetic phases in two-dimensional materials (arxiv.org)

Efficient Stochastic Optimisation via Sequential Monte Carlo (arxiv.org)

REMAL: Residual Equilibrium Manifold Active Learning for Surrogate-Based Multidisciplinary Design Analysis (arxiv.org)

Towards More General Control of Diffusion Models Using Jeffrey Guidance (arxiv.org)

Calibrating simplified vine copulas with a noise contrastive estimation approach (arxiv.org)

A Quadratic Order Reduction -- Gaussian Process Ordinary Differential Equation framework for the inference of Large Continuous Dynamical Systems (arxiv.org)

AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction (arxiv.org)

Diffusion-Network Alignment: An Efficient Algorithm and Explicit Probability Bounds (arxiv.org)

On McDiarmid's Inequality under Dependence via Approximate Tensorization of Entropy (arxiv.org)

A unified complexity bound for logconcave sampling (arxiv.org)

Two-Layer Linear Auto-Regressive Models Estimate Latent States (arxiv.org)

How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings? (arxiv.org)

Simultaneous Latent Budget Trees for Stratified Classification (arxiv.org)

ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization (arxiv.org)

Robust State-Conditional Feature-Weighted Jump Models for Temporal Clustering (arxiv.org)

Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression (arxiv.org)

Epistemic Uncertainty Is Not the Reducible Kind (arxiv.org)

Majority-of-Three is Optimal (arxiv.org)

Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency (arxiv.org)

Rapid mixing for Gibbs measures in Riemannian manifolds (arxiv.org)

Accelerating Speculative Diffusions via Block Verification (arxiv.org)

Reliability of Probabilistic Emulation of Physical Systems (arxiv.org)

TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data? (arxiv.org)

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment (arxiv.org)

Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach (arxiv.org)

Under What Conditions Can a Machine Become Genuinely Creative? (arxiv.org)

ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning (arxiv.org)

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints (arxiv.org)

MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment (arxiv.org)

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis (arxiv.org)

Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm (arxiv.org)

EPIG: Emotion-Based Prompting for Personalised Image Generation (arxiv.org)

Multi-Field Hybrid Retrieval-Augmented Generation for Maritime Accident Root Cause Analysis (arxiv.org)

Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda (arxiv.org)