AI News

Representing Time Series as Structured Programs for LLM Reasoning (arxiv.org)

Speculative Rollback Correction for Quality-Diverse Web Agent Imitation (arxiv.org)

Improving Crash Frequency Prediction from Simulated Traffic Conflicts Using Machine Learning Based Microsimulation (arxiv.org)

A Mathematical Theory of Value: a synthesis on goal-directed agency under resource constraints (arxiv.org)

Foresight: Iterative Reasoning About Clues that Matter for Navigation (arxiv.org)

EDEN: A Large-Scale Corpus of Clinical Notes for Italian (arxiv.org)

Competition and Diversity in Generative AI (arxiv.org)

WildIFEval: Instruction Following in the Wild (arxiv.org)

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning (arxiv.org)

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding (arxiv.org)

Meta-Learning Transformers to Improve In-Context Generalization (arxiv.org)

Reconstructing Template-Memorized Images from Natural Prompts (arxiv.org)

Authorship Attribution in Multilingual Machine-Generated Texts (arxiv.org)

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models (arxiv.org)

Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery (arxiv.org)

Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming (arxiv.org)

Improving Pre-trained Adult Glioma Segmentation Models Using only Post-processing Techniques (arxiv.org)

A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction (arxiv.org)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? (arxiv.org)

PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal Generation (arxiv.org)

Cluster Aggregated GAN (CAG): A Cluster-Based Hybrid Model for Appliance Pattern Generation (arxiv.org)

Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark (arxiv.org)

Agentic MPC for Semantic Control System Resynthesis (arxiv.org)

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs (arxiv.org)

Emerging Flexible Designs for Geospatial Multimodal Foundation Models (arxiv.org)

A Minimal Model of Bounded Trade-Off Screening in Multi-Attribute Choice (arxiv.org)

From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation (arxiv.org)

HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection (arxiv.org)

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents (arxiv.org)

Token Complexity Theory for AI-Augmented Computing (arxiv.org)

BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention (arxiv.org)

CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents (arxiv.org)

Free-Placement Optimization of Ground Station Locations for Low-Earth Orbit Satellites (arxiv.org)

M*: A Modular, Extensible, Serving System for Multimodal Models (arxiv.org)

EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence (arxiv.org)

LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data (arxiv.org)

SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems (arxiv.org)

AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages (arxiv.org)

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections (arxiv.org)

LLMs Can Better Capture Human Judgments--With the Right Prompts (arxiv.org)

Exploring How Agent Voice Accents Shape Human-AI Collaboration in K-12 Group Learning (arxiv.org)

SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning (arxiv.org)

Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids (arxiv.org)

Localizing Anchoring Pathways in Language Models (arxiv.org)

Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata (arxiv.org)

DIMOS: Disentangling Instance-level Moving Object Segmentation (arxiv.org)

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning (arxiv.org)

The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale (arxiv.org)

OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction (arxiv.org)

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models (arxiv.org)