AI News

Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents (arxiv.org)

Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning (arxiv.org)

FairLRF: Achieving Fairness through Sparse Low Rank Factorization (arxiv.org)

ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs (arxiv.org)

BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models (arxiv.org)

Active Learning Enables Generation of Molecules that Advance the Known Pareto Front (arxiv.org)

Uncertainty measurement for complex event prediction in safety-critical systems (arxiv.org)

Generalizing Adam to Manifolds for Efficiently Training Transformers (arxiv.org)

Reliable learning in challenging environments (arxiv.org)

Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations (arxiv.org)

Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators (arxiv.org)

LSR-Net: Learning the Forward Evolution Operator for Nonlinear Fluid Dynamics (arxiv.org)

Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion (arxiv.org)

Learning Lyapunov Operators for Nonlinear Systems (arxiv.org)

Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study (arxiv.org)

VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge (arxiv.org)

Fallacy Benchmarks Measure Scheme Recognition, Not Fallacy Detection (arxiv.org)

Topology-enhanced machine learning for speech signal processing (arxiv.org)

Learning Array Signal Topologies as Conditional Neural Manifolds (arxiv.org)

PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? (arxiv.org)

TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking (arxiv.org)

Deep learning emergent spacetime from fermionic spectral functions in holography (arxiv.org)

Variational Quantum Transformer Architecture for Synthetic Language Generation (arxiv.org)

COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads (arxiv.org)

ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware (arxiv.org)

Learning from Distributed Eyes: Leveraging Collaborative Perception for Automated Model Adaptation (arxiv.org)

Butterfly Effect and the Kinetic Energy Cascade in Probabilistic Machine Learning Weather Prediction Models (arxiv.org)

Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows (arxiv.org)

Decentralized Optimal Equilibrium Learning Over Dynamic Networks (arxiv.org)

Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems (arxiv.org)

SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis (arxiv.org)

Objective vs. Search: Decomposing What Makes a Good Tokeniser (arxiv.org)

A Zeroth-Order Paradigm for LLM Preference Alignment (arxiv.org)

Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation (arxiv.org)

Affora: A Design System for Agent-Friendly Interfaces (arxiv.org)

rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference (arxiv.org)

Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria (arxiv.org)

Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation (arxiv.org)

Securing quantum error correction against misleading advice from AI agents (arxiv.org)

Probabilistic Linear Explanations (arxiv.org)

RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control (arxiv.org)

MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents (arxiv.org)

TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse (arxiv.org)

Tabular Deep Learning vs Classical Machine Learning for Urban Land Cover Classification (arxiv.org)

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation (arxiv.org)

WordPolo: Evaluating Language Models Through Iterative Semantic Feedback (arxiv.org)

BadQubits: An LLM-Based Framework for Static Pre-Execution Detection of Structurally Harmful Quantum Circuits (arxiv.org)

Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Review (arxiv.org)

Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning (arxiv.org)

An Agentic Framework for Neuro-Symbolic Programming (arxiv.org)