AI News

Lingo_Research_Group at SemEval-2026 Task 9: Evaluating Prompt Variants for Polarization Detection (arxiv.org)

SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling (arxiv.org)

RRISE: Robust Radius Inference via a Surrogate Estimator (arxiv.org)

The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs (arxiv.org)

Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing (arxiv.org)

A Hybrid Approach For Malware Classification Using Secondary Features Fusion (arxiv.org)

LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks (arxiv.org)

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization (arxiv.org)

High-Precision APT Malware Attribution with Out-of-Scope Resilience (arxiv.org)

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)

Low-Frequency Shortcuts in Texture-Driven Visual Learning (arxiv.org)

What Makes Interaction Trajectories Effective for Training Terminal Agents? (arxiv.org)

Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative (arxiv.org)

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees (arxiv.org)

GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations (arxiv.org)

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks (arxiv.org)

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting (arxiv.org)

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation (arxiv.org)

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs (arxiv.org)

GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning (arxiv.org)

Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning (arxiv.org)

FORGE: Multi-Agent Graduated Exploitation and Detection Engineering (arxiv.org)

Decomposing how prompting steers behavior (arxiv.org)

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation (arxiv.org)

A Systematic Evaluation of Current Architectures in Wind Power Forecasting (arxiv.org)

Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics (arxiv.org)

Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach (arxiv.org)

AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses (arxiv.org)

FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems (arxiv.org)

PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers (arxiv.org)

Speech Emotion Recognition using Attention-based LSTM-Network with Residual Connection (arxiv.org)

SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts (arxiv.org)

ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents (arxiv.org)

RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting (arxiv.org)

Learning Coherent Representations: A Topological Approach to Interpretability (arxiv.org)

Effect of Demographic Bias on Skin Lesion Classification (arxiv.org)

What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents (arxiv.org)

Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning (arxiv.org)

A 3D Isovist World Model -- Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature (arxiv.org)

BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language (arxiv.org)

Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data Imputation (arxiv.org)

Dropstone 1.5 (www.producthunt.com)

America's Data Center Build-Out Is Falling Way Behind Schedule (www.wsj.com)

The Unreasonable Redundancy of Nature's Protein Folds (research.ligo.bio)

U of T researchers demonstrate AI worm could target any online device (www.utoronto.ca)

24 entreprises du département récompensées au salon « Fabriqué en Yvelines - EVASION (www.evasionfm.com)

The American Missile Crisis (research.contrary.com)

Microsoft's Project Solara Is an OS For Devices That Run AI Agents Instead of Apps (hardware.slashdot.org)

HHS is overriding peer review to require changes to research scope, design (www.science.org)