AI News

RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection (arxiv.org)

Reconstruction-Optimized Expert Pruning for Mixture-of-Experts Language Models (arxiv.org)

Feature Selection for Latent Factor Models (arxiv.org)

When Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-Diagnosis (arxiv.org)

MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories (arxiv.org)

Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning (arxiv.org)

Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment (arxiv.org)

Glass-Box Deep Reinforcement Learning for High-Speed Flow Control (arxiv.org)

Ontic state recovery through prediction (arxiv.org)

Representing short-term movement to reveal animal identity and learning progress (arxiv.org)

A Hybrid TFT-NBEATS Framework for Robust Multi-Horizon Photovoltaic Power Forecasting (arxiv.org)

Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE (arxiv.org)

RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials (arxiv.org)

When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects (arxiv.org)

The Show-Up Attack: When Subagents Win Over Their Supervisor (arxiv.org)

DuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech Agents (arxiv.org)

Beyond Experience: Knowledge-Guided Evolution for NPU Kernel Generation (arxiv.org)

Understanding the Benefits of Scaffolds through Computational Separations (arxiv.org)

Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments (arxiv.org)

You Are the Trigger: Speaker-Activated Backdoors (arxiv.org)

A Theoretical Analysis of Environment-Aware Out-of-Distribution Detection for Vision-Language Models (arxiv.org)

From Encoding to Generation: Towards Empathetic Large Language Models (arxiv.org)

TriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZ (arxiv.org)

When Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design (arxiv.org)

Dancing Diffusion: Learning Continuous Programs for Image Generation and Editing (arxiv.org)

On Johnson-Lindenstrauss Transforms for Byzantine-Robust Optimization (arxiv.org)

Unsupervised Head Network Personalization for Split Computing via Federated Learning (arxiv.org)

TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment (arxiv.org)

Slot-JEPA: Object-Structured Prediction Interfaces for Latent World Models (arxiv.org)

IECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for Electrocardiogram (arxiv.org)

When Momentum Helps Polyak--Ruppert Averaging (arxiv.org)

RANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation Rewards (arxiv.org)

From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks (arxiv.org)

FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model (arxiv.org)

InsightRAG: Aggregating Distributed Scholarly Judgments for Scientific Survey Generation (arxiv.org)

Polyscene: Scenario Planning as Diversity Planning (arxiv.org)

A Semi-Analytical Inference Framework for Structural Causal Models (arxiv.org)

Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck (arxiv.org)

Weight Space Learning for Certifiable Few-shot Transfer Learning (arxiv.org)

Interruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary Overrides (arxiv.org)

MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses (arxiv.org)

ChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart Reasoning (arxiv.org)

Is Sycophancy a Form of In-Context Updating? (arxiv.org)

Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere? (arxiv.org)

Dissecting the Impact of Model Misspecification in Data-driven Optimization (arxiv.org)

PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models (arxiv.org)

Federated Learning: From Theory to Practice (arxiv.org)

Accelerating Optimization via Differentiable Stopping Time (arxiv.org)

Rethinking Generalization in Knowledge Graph Embedding: An Empirical Study and Sparse Peak Regularization (arxiv.org)

S-Agent 2.0: Spatial Reasoning with a General Coding Agent (arxiv.org)