AI News

EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale (arxiv.org)

MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated Learning (arxiv.org)

Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data (arxiv.org)

From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good (arxiv.org)

TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription (arxiv.org)

CausalArena: Benchmarking Causal Discovery in the Foundation Model Era (arxiv.org)

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search (arxiv.org)

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement (arxiv.org)

AdamX: Cosine similarity meets gradient descent (arxiv.org)

Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport (arxiv.org)

Thinking with Looped Flows (arxiv.org)

Dynamic language model representations for multi-objective reaction optimisation (arxiv.org)

Reflex-Informed Neuromuscular Reinforcement Learning for Muscle-Driven Locomotion (arxiv.org)

Predicting Privacy Leakage from Weight Spectral Density (arxiv.org)

Why Does Post-Training Quantization Work? (arxiv.org)

Learnware and AI Model Management System (arxiv.org)

Musec: MomentUm SpEctral Clipping for Stable Muon-type Training (arxiv.org)

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution (arxiv.org)

LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy Analytics (arxiv.org)

A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph (arxiv.org)

Particle GFlowNets: Rethinking Generative Marginalization Models (arxiv.org)

RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding (arxiv.org)

Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs (arxiv.org)

A variational physics-informed graph neural network for heterogeneous solid mechanics (arxiv.org)

New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models (arxiv.org)

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN) (arxiv.org)

Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning (arxiv.org)

Halo: Improving forecast accuracy through heteroscedastic estimation (arxiv.org)

Zero-shot rib design: merging training-free generative prior with topology optimization (arxiv.org)

Hologram Representation via Quadratic Phase Gaussian Splatting (arxiv.org)

DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis (arxiv.org)

Combining Synthetic and Real Data for Low-Resource Historical OCR: A Manchu Case Study (arxiv.org)

Prevalence Determines Precision:Silent Contamination in Detector-Defined Datasets (arxiv.org)

Byzantine-Robust Federated Fire Detection with a Rotating Coordinator (arxiv.org)

Artificial Intelligence Algorithms for the Detection of Pathologies Related to Lung Cancer through Image Analysis using Convolutional Neural Networks and Data Augmentation: a systematic mapping of the literature (arxiv.org)

GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models (arxiv.org)

Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints (arxiv.org)

The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes (arxiv.org)

Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification (arxiv.org)

Local Robustness Quantification for Naive Bayes Classifiers and Generative Forests: a General Approach (arxiv.org)

Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs (arxiv.org)

Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development (arxiv.org)

A Dynamic Fusion Large Language Model for Traffic Flow Prediction (arxiv.org)

MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions (arxiv.org)

Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer (arxiv.org)

Polyhedral Geometry of Time-to-First-Spike Neural Networks (arxiv.org)

Legible Failures: Detecting and Repairing In-Context Binding Errors (arxiv.org)

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving (arxiv.org)

Convex Optimization with Nested Evolving Feasible Sets (CONES) under Time-Varying Loss Functions (arxiv.org)

Semi-Tensor Product-Based Multi-Term Randomized T-SVD and Its Visual Applications (arxiv.org)