AI News

AI Mindmeld: A Latent Interconnect Protocol (arxiv.org)

When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations (arxiv.org)

Flow-based Spectral Kernel Learning for Nonstationary Attention (arxiv.org)

WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting (arxiv.org)

High-Value Training Data from Noisy, Diverse Sources (arxiv.org)

xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs (arxiv.org)

Nonparametric autoregressive estimation of probability distributions with parallel gradient boosting (arxiv.org)

Prediction Uncertainty Controlled Computer Model Calibration (arxiv.org)

Deep Learning for Random Objects in Metric Spaces: Beyond Manifold Assumptions (arxiv.org)

Width and Depth Limits Commute During Training (arxiv.org)

Vision Transformers for Estimating Irradiance Using Data Scarce Sky Images (arxiv.org)

Lifetime-valid decisions by continually evolving AI analysts (arxiv.org)

Penalized Fair Regression for Multiple Groups in Chronic Kidney Disease (arxiv.org)

Residual Calibration via Local Feature-Space Refinement (arxiv.org)

Transformers with CoT Discover Heavy-Ball Acceleration Through Training (arxiv.org)

Metric Conformal Prediction via the Conditional Expected Local Radius (arxiv.org)

Dimension-free regimes for unadjusted Langevin in ridge-separable models: A subspace robust Wasserstein analysis (arxiv.org)

Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms (arxiv.org)

Scaling Multilingual Pretraining of Pixel Language Models (arxiv.org)

Benchmarking Model Compression Techniques Across Heterogeneous Edge Platforms: A Predictive Maintenance Use Case for Rotating Machinery (arxiv.org)

DiffLTM: Continuous Diffusions Large Tabular Models for Conditional Generation (arxiv.org)

Sparse Equation Matching: A Derivative-Free Learning for General-Order Dynamical Systems (arxiv.org)

Agentic Music Post-Production (arxiv.org)

Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training (arxiv.org)

A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined (arxiv.org)

Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research (arxiv.org)

Broadband Mid-Wave Infrared Imaging Enabled by All-Silicon Hyperboloid Metalens (arxiv.org)

Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks (arxiv.org)

Agentic Video Understanding: A Survey (arxiv.org)

Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration (arxiv.org)

GRAFT: Restoring the Missing Sampling Interface in Continuous Diffusion Language Models (arxiv.org)

PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety (arxiv.org)

Agentic Verified Optimization of Real-World Software (arxiv.org)

AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents (arxiv.org)

Quantum-Inspired Optimization Process for Data Imputation (arxiv.org)

Post-Hoc Feature Selection Layer for Neural Networks Interpretability (arxiv.org)

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition (arxiv.org)

Mitigating Reward Hacking in Preference Reward Models with Evolving Penalties (arxiv.org)

Building Auditable AI Text Detectors with Sparse Autoencoders (arxiv.org)

RocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers (arxiv.org)

ReSeg: Retraining-free segmentation of abdominal organs via generalizable semantic representation learning (arxiv.org)

Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning (arxiv.org)

FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather (arxiv.org)

aggmetrics: Aggregating Classification Performance Measures for Machine Learning (arxiv.org)

One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection (arxiv.org)

Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains (arxiv.org)

MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking (arxiv.org)

Algorithmic Reflectivity in Large Language Models: Methodological Study of Linguistic Structure in Mentalization (arxiv.org)

Risk-Aware Alignment Must Incorporate Reward Uncertainty (arxiv.org)

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning? (arxiv.org)