AI News

Emergence of Context Characteristics Sensitivity in Large Language Models (arxiv.org)

Disjoint Generation of Synthetic Data (arxiv.org)

Convergence Bound and Critical Batch Size of Muon Optimizer (arxiv.org)

Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment (arxiv.org)

The Sample Complexity of Parameter-Free Stochastic Convex Optimization (arxiv.org)

Formalizing Learning from Language Feedback with Provable Guarantees (arxiv.org)

Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration (arxiv.org)

"So There's a Catch-22 Here": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency (arxiv.org)

GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models (arxiv.org)

The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In (arxiv.org)

Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR (arxiv.org)

RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT (arxiv.org)

LCAM: A Framework for Diagnosing Interactional Alignment Failures in Con-versational AI (arxiv.org)

Human-Centered Benchmarking of Driver Monitoring Models (arxiv.org)

Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data (arxiv.org)

Continual Quadruped Robots Coordination via Semantic Skill Discovery (arxiv.org)

Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method (arxiv.org)

Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions (arxiv.org)

"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory (arxiv.org)

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? (arxiv.org)

Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning (arxiv.org)

LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty (arxiv.org)

phepy: Visual benchmarks and improvements for out-of-distribution detectors (arxiv.org)

AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Critics (arxiv.org)

Advancements in Machine Learning and Deep Learning for Early Detection and Management of Mental Health Disorder (arxiv.org)

ePC: Fast and Deep Predictive Coding in Digital Simulation (arxiv.org)

Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligence (arxiv.org)

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching (arxiv.org)

Zero and Few Shot Load Forecasting with Large Language Models (arxiv.org)

Modeling Stochastic Conditional Dynamics from Sparse Observations via Kernel-Stabilized Flow Matching (arxiv.org)

EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets (arxiv.org)

What's the Point? Spatial Grammar & Index Resolution for Sign Language Processing (arxiv.org)

GIScholarBench: Benchmarking LLM Overconfidence in GIS Research (arxiv.org)

Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems (arxiv.org)

Voting Protocols as Coordination Mechanisms for Role-Constrained Multi-Agent Tutoring Systems (arxiv.org)

Discovering Data Structures: Nearest Neighbor Search and Beyond (arxiv.org)

Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design (arxiv.org)

Federated Large Language Models: Current Progress and Future Directions (arxiv.org)

Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprinting (arxiv.org)

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape (arxiv.org)

Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning (arxiv.org)

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment (arxiv.org)

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence (arxiv.org)

Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation (arxiv.org)

Summarization is Not Dead Yet (arxiv.org)

CATPO: Critique-Augmented Tree Policy Optimization (arxiv.org)

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook (arxiv.org)

Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems (arxiv.org)

Improving Multimodal Reasoning via Worst Dimension Optimization (arxiv.org)

Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings (arxiv.org)