AI News

A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure (arxiv.org)

Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction (arxiv.org)

Agentic Search Spaces for Tabular Machine Learning (arxiv.org)

Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations (arxiv.org)

Differentially Private Semantic Plans for Aggregate Insight Generation (arxiv.org)

Scaling Laws for Physics-Aware ACOPF Surrogate Learning (arxiv.org)

The record is part of the task: matched-record evaluation of text classifiers across maintenance, safety and recall reporting (arxiv.org)

Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning (arxiv.org)

Test-Time Unlearning via Sparse Autoencoder (arxiv.org)

How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning (arxiv.org)

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration (arxiv.org)

Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It (arxiv.org)

Z-Loss Backward Geometry in Dense Output Heads and Sparse Routers (arxiv.org)

LLM Inference in a Flash! (arxiv.org)

LLMs as Master Forgers: Generating Synthetic Time Series Data for Manufacturing (arxiv.org)

A Decision-Support Audit Protocol for Supervision Drift in Proxy-Labeled Credit-Risk Prediction (arxiv.org)

SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation (arxiv.org)

Evaluating Open-Weight E-Commerce Agents with Environment-Grounded Verification (arxiv.org)

Distilling Foundation Models for Agentic What-If Reasoning:Cost, Latency, and Governance in a Hybrid LLM+SLM Architecture (arxiv.org)

Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups (arxiv.org)

Schema-Adaptive Action-Conditioned JEPA for Cross-Machine CNC Transfer under Partial Sensor Overlap (arxiv.org)

Beyond Distribution Matching: Semantics-Consistent Tabular Diffusion with Weak Semantic Priors (arxiv.org)

A Dynamic Aggregation Strategy Enhanced Efficient Global Optimization Algorithm for Solving High-Dimensional Turbomachinery Design Problems (arxiv.org)

A panoramic aerodynamic performance prediction method for turbomachinery cascades using transformer-enhanced neural operator (arxiv.org)

You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition (arxiv.org)

HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning (arxiv.org)

Driver Behavior Estimation at Signalized Intersections Using a Physics-Constrained Decision-Conditioned Autoregressive Transformer (arxiv.org)

OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning (arxiv.org)

Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents (arxiv.org)

Signed p-adic Residual Encodings of Finite-Domain All-Different Systems with a Sudoku Case Study (arxiv.org)

POSPAN: Position-Constrained Span Masking for Language Model Pre-training (arxiv.org)

Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems (arxiv.org)

Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation (arxiv.org)

Semi-Supervised Learning-Based Genetic Biomarkers Dataset for Multiple-Stage Hepatocellular Carcinoma Prediction (arxiv.org)

SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning (arxiv.org)

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation (arxiv.org)

ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents (arxiv.org)

FlexEE: Self-Speculative and KV-Compatible Early Exiting for Offloading-Aware LLM Inference (arxiv.org)

Affect-Prototype Guided Fusion for Open-Vocabulary Incomplete Multi-modal Emotion Recognition (arxiv.org)

AntennaFlow: A Generative Flow Model for Offset Correction in Phaseless Antenna Testing (arxiv.org)

QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling (arxiv.org)

Bridging Learned Visual Perception and Symbolic Belief-Space Planning (arxiv.org)

CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarms (arxiv.org)

Execution Flexibility in Automated Planning: A Comparative Evaluation of Deordering and Reordering Strategies (arxiv.org)

Can We Do Interpretable NLI with Graphs Based on Atomic Propositions? (arxiv.org)

Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models (arxiv.org)

Integrating the Analytic Hierarchy Process with Large Language Models for Transparent Multi-Criteria Decision-Making (arxiv.org)

Coverage-Aware Virtual IMU Augmentation for Low-Resource Human Activity Recognition (arxiv.org)

Turn-level Multiscale Density Ratio Estimation for LLM Agents (arxiv.org)

Beyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition (arxiv.org)