AI News

Testing Algebraic Complete Intersections (arxiv.org)

Prediction-Powered Data Fusion for Treatment Effect Estimation (arxiv.org)

Estimating great expectations under autoregressive language models with potentials (arxiv.org)

Density Ratio Estimation with Stein Displacement Fields (arxiv.org)

Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics (arxiv.org)

D-SLR: The Disjoint Row-Sparse plus Low-Rank Decomposition (arxiv.org)

How Many Directions Must a Truncated Diffusion Sampler Retain? Matching Bounds Under Power-Law Spectra (arxiv.org)

Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks (arxiv.org)

SPD-MetaFormer is what you need for small-data brain decoding (arxiv.org)

Sequential Conditional Independence Testing with Machine Learning Models (arxiv.org)

Decision-Sufficient Posterior Approximation (arxiv.org)

Tight Bounds for Equivalence Testing with Non-Adaptive Conditional Samples (arxiv.org)

When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization (arxiv.org)

Regularized Small Area Estimation with Graph Laplacian Benchmarking priors (arxiv.org)

From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon (arxiv.org)

Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD (arxiv.org)

Automated Detection of Match Phases in Football from Spatio-Temporal Tracking Data Using Graph Neural Networks (arxiv.org)

Verification and Self-Improvement in Agentic AI: Foundations and Limits (arxiv.org)

Optimal random quantisers for spherically symmetric distributions (arxiv.org)

Exploiting Gradients in Bayesian Inference of Expensive Simulators (arxiv.org)

Credal Machine Learning for Risk-Averse Decision Making (arxiv.org)

Verification with Transfer: Exact Information Frontiers and Their Price in Calls (arxiv.org)

The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate (arxiv.org)

Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity (arxiv.org)

Closing the Horizon Gap in Policy Optimization for Adversarial MDPs (arxiv.org)

Self-sufficient Independent Component Analysis for Demixing Flows (arxiv.org)

Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders (arxiv.org)

GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary (arxiv.org)

Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents (arxiv.org)

Plan-and-Patch: Diffusion Language Models for Agentic Planning (arxiv.org)

Whose Ground Truth? Embracing Ambiguity in Human-Centered AI (arxiv.org)

AI-Mediated Self: How HCI Defines and Relates to the Self (arxiv.org)

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents (arxiv.org)

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces (arxiv.org)

From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning (arxiv.org)

CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis (arxiv.org)

Learning from Hetero Density for Cryo-EM Protein Reconstruction (arxiv.org)

MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views (arxiv.org)

Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy (arxiv.org)

Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals (arxiv.org)

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies (arxiv.org)

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems (arxiv.org)

AgentEvolver: System-Wide Self-Evolution Through Task Execution (arxiv.org)

Puffin: Probabilistic Learning of Spatial Detail From Coarse Observations (arxiv.org)

Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents (arxiv.org)

LLM Persona Unlearning (arxiv.org)

Parameter-Free Zeroth-Order Optimization with Ellipsoidal Sampling (arxiv.org)

Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving (arxiv.org)

CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data (arxiv.org)

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization (arxiv.org)