AI News

Towards Diverse Scientific Hypothesis Search with Large Language Models (arxiv.org)

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting (arxiv.org)

Embedding Hybrid Systems into Continuous Latent Vector Fields (arxiv.org)

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting (arxiv.org)

Geometry-Aware Reinforcement Learning for 2D Irregular Nesting (arxiv.org)

Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents (arxiv.org)

Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization (arxiv.org)

Predictive Assistance and the Temporal Dynamics of Exploratory Compression (arxiv.org)

From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs (arxiv.org)

IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts (arxiv.org)

Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning (arxiv.org)

Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fixed-\texorpdfstring{$\delta$}{delta} Alignment (arxiv.org)

PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models (arxiv.org)

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models (arxiv.org)

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization (arxiv.org)

Event-Driven Reinforcement Learning Enables Long-Horizon Control in Semiconductor Fabrication (arxiv.org)

Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey (arxiv.org)

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition (arxiv.org)

Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports (arxiv.org)

SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation (arxiv.org)

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence (arxiv.org)

A Theory on Flow Matching with Neural Networks (arxiv.org)

A Note on the Strategic Confinement Problem (arxiv.org)

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines (arxiv.org)

Uncertainty-Aware Motion Planning for Autonomous Driving in Mixed Traffic Environment (arxiv.org)

WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory (arxiv.org)

On the Controllability-Fidelity Frontier in Diffusion Editing (arxiv.org)

Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter (arxiv.org)

Stochastic weather generators for high-frequency wind vector time series (arxiv.org)

Towards Critical Branching Mechanism in Recurrent Neural Networks (arxiv.org)

Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads (arxiv.org)

Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics (arxiv.org)

JGRA: Jacobian Geometry Robustness Assessment in NISQ Noise-Aware Quantum Neural Networks (arxiv.org)

Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions (arxiv.org)

GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation (arxiv.org)

CodeAlchemy: Synthetic Code Rewriting at Scale (arxiv.org)

SoK: Colluding Adversaries in Machine Learning Pipelines (arxiv.org)

Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning (arxiv.org)

FOGO: Forgetting-aware Orthogonalization Optimizer (arxiv.org)

Human-AI Coordination Zones: A Framework for Designing Human-in-the-Loop Experiences with Agentic AI (arxiv.org)

LLM-Based Code Documentation Generation and Multi-Judge Evaluation (arxiv.org)

Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis (arxiv.org)

Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation (arxiv.org)

Embodiment-conditioned Generalist Control for Multirotor Aerial Robots (arxiv.org)

++nnU-Net: Scaling nnU-Net with Prefix-Based Data Augmentation (arxiv.org)

MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents (arxiv.org)

Correcting Variable Importance Scored by Random Forests (arxiv.org)

On-sky demonstration of reinforcement learning for adaptive optics control (arxiv.org)

Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning (arxiv.org)

EstRTL: Functional Estimation Guided RTL Code Generation (arxiv.org)