AI News

An Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling (arxiv.org)

Why machines will still not rule the world (arxiv.org)

Universal Textual Teaching for LLMs (arxiv.org)

Bayesian Optimisation under State-Preservation Constraints (arxiv.org)

Large-Scale Benchmarking of Quantum Neural Network Configurations for Financial Time Series Forecasting (arxiv.org)

Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning (arxiv.org)

Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models (arxiv.org)

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution (arxiv.org)

Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes (arxiv.org)

When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation (arxiv.org)

Instruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization (arxiv.org)

Using Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation (arxiv.org)

AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting (arxiv.org)

A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning (arxiv.org)

Few-Step Generation via Data-Space Iteration (arxiv.org)

Q-Shaped Options for Hierarchical Reinforcement Learning (arxiv.org)

SCORE: Spectral Correlation Estimation for Multivariate Gaussians (arxiv.org)

MPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation (arxiv.org)

CausalDreamer: Learning Predictive World Models with Latent Disentanglement (arxiv.org)

Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits (arxiv.org)

InterviewPlayground: A Simulation Environment for Evaluating AI Interviewers (arxiv.org)

PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary (arxiv.org)

Complexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks (arxiv.org)

An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation (arxiv.org)

MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation (arxiv.org)

MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation (arxiv.org)

A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space (arxiv.org)

How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices (arxiv.org)

LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs (arxiv.org)

The Polytopal Neural Network (arxiv.org)

Agentic-TTT: Training test-time policy for test-time training (arxiv.org)

Example-driven Parametrisations for Bayesian Shape Optimisation (arxiv.org)

Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability (arxiv.org)

Interval-valued SHAP in Tree-Based Models (arxiv.org)

Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework (arxiv.org)

Understanding Latent-Dimension Scaling in Dynamical-System Learning through Spectral Reliability (arxiv.org)

GRPODropout: Less is More for Online Reinforcement Learning Rollouts (arxiv.org)

DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method (arxiv.org)

LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs (arxiv.org)

Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks (arxiv.org)

Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models (arxiv.org)

What Output-Only Review Cannot Verify: Study Contracts for Research Agents (arxiv.org)

Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding (arxiv.org)

Structure Tax: How Structured Output affects LLMs Performance (arxiv.org)

Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems (arxiv.org)

Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces (arxiv.org)

Onboard Marine Anomaly Detection on $\Phi$sat-2: From Simulation-Based Development to In-Orbit Demonstration (arxiv.org)

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents (arxiv.org)

Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning (arxiv.org)

In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control (arxiv.org)