AI News

PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting (arxiv.org)

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection (arxiv.org)

How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing (arxiv.org)

Optimal Rates for Agentic Networked Information Aggregation (arxiv.org)

Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation (arxiv.org)

ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies (arxiv.org)

Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network (arxiv.org)

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair (arxiv.org)

MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate (arxiv.org)

MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain (arxiv.org)

CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation (arxiv.org)

Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning (arxiv.org)

PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation (arxiv.org)

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents (arxiv.org)

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification (arxiv.org)

SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection (arxiv.org)

Attention-guided super-resolution of 4D flow MRI in carotid arteries (arxiv.org)

RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents (arxiv.org)

TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks (arxiv.org)

ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems (arxiv.org)

MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression (arxiv.org)

VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition (arxiv.org)

How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI (arxiv.org)

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection (arxiv.org)

How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions (arxiv.org)

Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Experiment Tracking (arxiv.org)

Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection (arxiv.org)

A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support (arxiv.org)

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors (arxiv.org)

A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning (arxiv.org)

A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment (arxiv.org)

AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics (arxiv.org)

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization (arxiv.org)

CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls (arxiv.org)

When Linguistic and Internal Confidence Diverge in Large Language Models (arxiv.org)

Harness-agnostic detection and immunization of reward hacking in self-evolving language models (arxiv.org)

Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning (arxiv.org)

Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems (arxiv.org)

Cross-modal triage network: a multimodal deep learning framework for severity-based triage and visual explainability in chest radiographs (arxiv.org)

Ultrasound-Based Prediction of Cirrhosis Decompensation Using Large-Scale Computer Vision Models (arxiv.org)

Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models (arxiv.org)

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? (arxiv.org)

The History Is the Detector: Executing CVE Patch History, End-to-End (arxiv.org)

Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool (arxiv.org)

When LLM Decompilers Recompile More and Preserve Less (arxiv.org)

What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies (arxiv.org)

Reflection-aware Generative Novel View Synthesis (arxiv.org)

A Sim-to-Real Study of Surface-Code Decoder Benchmarking (arxiv.org)

RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments (arxiv.org)

Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction (arxiv.org)