AI News

Multi-Agent Conformal Prediction with Personalized Statistical Validity (arxiv.org)

Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment (arxiv.org)

Causal Density Functions (arxiv.org)

Robust inference for risk heterogeneity under group imbalance (arxiv.org)

Revisiting Neural Processes via Fourier Transform and Volterra Series (arxiv.org)

Functional Clustering of Survival Data via Smoothed Log-Hazard Trajectories: A Risk-Dynamics Perspective (arxiv.org)

Statistical Inference on Gradient Flows (arxiv.org)

Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors (arxiv.org)

FlowSDR: Sufficient Dimension Reduction via Conditional Normalizing Flows (arxiv.org)

Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks (arxiv.org)

Transferring Information Across Interventions in Causal Bayesian Optimization (arxiv.org)

Fast Generalization after Interpolation via Critically Damped Momentum Optimization (arxiv.org)

Approximating $f$-Divergences with Rank Statistics (arxiv.org)

Semi-Supervised Hyperbolic Hierarchical Clustering with Set-Level Structural Priors (arxiv.org)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL (arxiv.org)

MINTS: Minimalist Thompson Sampling (arxiv.org)

Data-Automated Policy Learning for Nonlinear Welfare (arxiv.org)

Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits (arxiv.org)

Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler (arxiv.org)

Flow-Transformed Implicit Processes for Function-Space Variational Inference (arxiv.org)

PliableBVS: A flexible Bayesian variable selection method for modeling interactions with mandatory modifying variables (arxiv.org)

Query-Limited Community Recovery in Stochastic Block Models (arxiv.org)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs (arxiv.org)

TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents (arxiv.org)

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise (arxiv.org)

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts (arxiv.org)

MindClaw: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention (arxiv.org)

Before the Model Learns the Bug:Fuzzing RLVR Verifiers (arxiv.org)

Deep Learning as the Disciplined Construction of Tame Objects (arxiv.org)

Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes (arxiv.org)

Variance-sensitive Thompson sampling for generalised linear bandits, revisited (arxiv.org)

Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG (arxiv.org)

EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing (arxiv.org)

ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression (arxiv.org)

CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation (arxiv.org)

Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking (arxiv.org)

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision (arxiv.org)

Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches (arxiv.org)

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification (arxiv.org)

Torus Graphs for Large Scale Neural Phase Analysis (arxiv.org)

TabChange: Precise Attribute Changes in Tabular Data (arxiv.org)

Saliency-Aware Model Merging (arxiv.org)

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation (arxiv.org)

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation (arxiv.org)

Emergent Ordinal Geometry in Transformers Trained on Local Comparisons (arxiv.org)

Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts (arxiv.org)

"Skill issues'': data-centric optimization of lakehouse agents (arxiv.org)

The Case for Model Science: Verify, Explore, Steer, Refine (arxiv.org)

Can LLM Agents Sustain Long-Horizon Organizational Dynamics? (arxiv.org)

Application of Algorithms in Energy-Efficient Design Platforms for Green Building (arxiv.org)