AI News

Machine learning-assisted calibration of Agent-based Models: surrogate-based optimization with Genetic Algorithm and Particle Swarm Optimization (arxiv.org)

CANAL: Channel-Aware Noise Allocation for Differentially Private Feature Distillation in Medical Image Segmentation (arxiv.org)

Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals (arxiv.org)

MANAS-2: Constrained Reconstruction for EEG Foundation Models (arxiv.org)

JaxAHT: A JAX-Based Library for Ad Hoc Teamwork (arxiv.org)

Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks (arxiv.org)

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models (arxiv.org)

SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Science (arxiv.org)

Large-scale bioacoustic detection using semantic segmentation: a deep learning framework applied to fin whale calls in ocean-bottom seismometer recordings (arxiv.org)

Windowed A-K-MDP (arxiv.org)

Recoverability as a System Primitive for Long-Horizon AI Agents (arxiv.org)

Enhancing Event Candidate Acquisition for Event Linking (arxiv.org)

GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents (arxiv.org)

Cost Characterization of Vertically Partitioned Federated Knowledge Graphs (arxiv.org)

FedV-KGQA in Practice: Design Lessons and an Interactive Prototype (arxiv.org)

Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself (arxiv.org)

Solar Intelligence (arxiv.org)

Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents (arxiv.org)

$\tau$-Elicitation: Benchmarking multi-turn entity extraction in voice agents (arxiv.org)

FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks (arxiv.org)

How User-AI Mistreatment Occurs and Matters in Conversational Systems? (arxiv.org)

Causal multi-modal AI for personalized chemosensitivity prediction (arxiv.org)

Planning or Learning: Reliability and Cost in Multi-Asset Maintenance (arxiv.org)

Stochastic Gradient Descent over P2 (arxiv.org)

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction (arxiv.org)

Ergodic Control and Controlled Diffusion for Robot Learning: Review and Tutorial (arxiv.org)

Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning (arxiv.org)

Beyond Point Forecasts: A Survey on Probabilistic Forecasting for Time Series and Spatiotemporal Data (arxiv.org)

Disentangling Representation Evolution in Transformers through Directional Decomposition (arxiv.org)

Learning Metastable Dynamics (arxiv.org)

Sublinear Sketches for Approximate Nearest Neighbor and Kernel Density Estimation (arxiv.org)

Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis (arxiv.org)

From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization (arxiv.org)

Noise-Adaptive Conformal Classification with Marginal Coverage (arxiv.org)

N$^2$: A Unified Python Package and Test Bench for Nearest Neighbor-Based Matrix Completion (arxiv.org)

Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models (arxiv.org)

LLM-Enhanced Multi-Agent Reinforcement Learning for Unified Electric Vehicles-Charging Station-Grid Optimization in Public Charging Systems (arxiv.org)

CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models (arxiv.org)

Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains (arxiv.org)

Discovering Hierarchy-Grounded Domains with Adaptive Granularity for Clinical Domain Generalization (arxiv.org)

Data Security in Large Language Models: Risks, Defense, and Directions (arxiv.org)

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores (arxiv.org)

Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuum (arxiv.org)

TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control (arxiv.org)

IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives (arxiv.org)

Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never had (arxiv.org)

MOSCOPT: Mixture-of-Skills Collective Optimization for LLM Agents (arxiv.org)

Dynamic Learning Solutions: A System for Personalized Educational Video Generation (arxiv.org)

Question's Gambit: The First Move Matters in Agentic Deep Search (arxiv.org)

Safety Signals to Verify NetOps Agents with Action-Level Granularity (arxiv.org)