AI News

Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation (arxiv.org)

Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning (arxiv.org)

Reinforcement learning for Quantum Tiq-Taq-Toe (arxiv.org)

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams (arxiv.org)

Show-Harness: Just a VLM Agent Can Play Robots (arxiv.org)

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents (arxiv.org)

Project Qualia: Recovering Experiential Music Structure from Session Co-occurrence Data (arxiv.org)

Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions (arxiv.org)

scDEFT: A deep learning framework for drug-effect prediction and counterfactual reasoning (arxiv.org)

TailProp: content-adaptive light- and heavy-tailed propagation for vision (arxiv.org)

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents (arxiv.org)

Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models (arxiv.org)

Generative AI for Analysts (arxiv.org)

MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation (arxiv.org)

IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier (arxiv.org)

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization (arxiv.org)

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs (arxiv.org)

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation (arxiv.org)

ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding (arxiv.org)

Multimodal Taxonomic Conditioning for Generative Plankton Imagery (arxiv.org)

Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System (arxiv.org)

When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text (arxiv.org)

Distributed Physical Layer Authentication and Collaborative RSMA in Non-Terrestrial Networks via Graph Reinforcement Learning (arxiv.org)

JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition (arxiv.org)

ConvMem: Convolutional Memory for Long-Context Reasoning (arxiv.org)

Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather Alerts (arxiv.org)

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting (arxiv.org)

SoK: Privacy Attacks on Machine Learning via Explainable AI (arxiv.org)

From Cycle Space to Cycle Manifold: Limits and Achievability of Blind False Data Injection Attacks (arxiv.org)

Numbat: Building and Verifying a Self-Contained Machine-Learning Stack (arxiv.org)

Sequence-Informed Geometric Evaluation of RNA 3D Structures (arxiv.org)

Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection (arxiv.org)

A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning (arxiv.org)

Rethinking Radiomap Blind Prediction with Limited Environment and Configuration Representations (arxiv.org)

Diversity of EML-type operators (arxiv.org)

CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting (arxiv.org)

A Fragility Spectrum for Recursive Language-Model Training (arxiv.org)

The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems (arxiv.org)

Generative Replay Mitigates Sample Starvation in Quantum Architecture Search (arxiv.org)

EVTradeMatch: A Mobility-Aware Multi-Objective Matching Framework for EV--EV Energy Trading (arxiv.org)

Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks (arxiv.org)

The Platonic brain bridge hypothesis: human brain networks as an architectural prior for omni models (arxiv.org)

Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction (arxiv.org)

False positive bias in AI-powered speech-based cognitive screening for multilingual English speakers in the UK (arxiv.org)

Improving Faint Object Detection for Space Situational Awareness with Variational Autoencoders (arxiv.org)

Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction (arxiv.org)

Kernel-Managed Shared Memory for System-Wide Personalization (arxiv.org)

What Should an Agent Forget? Separating What Is Stored from What Is Used (arxiv.org)

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove (arxiv.org)

Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning (arxiv.org)