AI News

Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model (arxiv.org)

Behavioral Cloning Outperforms Entropy-Regularized RL: Critic-Driven Failure of Actor-Critic Methods on Adaptive Tumor Treatment (arxiv.org)

Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach (arxiv.org)

Data Efficient Sample Selection for In-Context Learning (arxiv.org)

Tracking the Moving Frontier: Long-Short Term Advantage Estimator (arxiv.org)

LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery (arxiv.org)

DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing (arxiv.org)

When Retain Constraints Conflict: Mitigating Forget-Retain Interference in Tabular Data (arxiv.org)

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training (arxiv.org)

HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care (arxiv.org)

Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning (arxiv.org)

Constrained Bayesian Optimization for Hierarchical Federated Learning in IoT Networks for Plant Disease Classification (arxiv.org)

Feature Superposition in Neural Networks: From Theory to Practice (arxiv.org)

PPIM: Pennes Physics-Informed Mamba for Heat-Source-Conditioned 3D Bioheat Simulation (arxiv.org)

Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate (arxiv.org)

Learning Adaptive SED for heterogeneous load balancing (arxiv.org)

Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning (arxiv.org)

From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models (arxiv.org)

Constrained Online Learning with Noisy Constraint Values (arxiv.org)

The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists (arxiv.org)

PCSDiff: Diffusion-Based Bias Correction and Super Resolution Toward Practical Operational Medium-Term Precipitation Forecast (arxiv.org)

Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective (arxiv.org)

Steering Interference Reflects the Model's Defaults, Not the Behavior Directions (arxiv.org)

Fine-grained Distributed Backdoor Attacks in Federated Learning (arxiv.org)

AF-Mamba: Efficient Long-Term Signal Modeling for Early Prediction of Atrial Fibrillation Onset (arxiv.org)

Continual Learning Mechanisms Compose for Long-Horizon Memorization (arxiv.org)

NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts (arxiv.org)

Efficient Learning and Symmetry Discovery under Exact Invariances (arxiv.org)

Disentangling Steering Vectors (arxiv.org)

AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM (arxiv.org)

TrojanWorld: Backdooring World-Model Agents via Imagination Steering (arxiv.org)

Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching (arxiv.org)

PhysSAE: Mechanistic Interpretability with Sparse Autoencoders (arxiv.org)

Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols (arxiv.org)

IXPLORE: Bounded Ideal Point Estimation with Grid-Based Uncertainty Quantification (arxiv.org)

Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning (arxiv.org)

SkillAlign: Aligning Skill Interfaces for LLM-based Agents (arxiv.org)

World Models Under Asynchronous Sensor Observations (arxiv.org)

Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Prediction: When Not All Errors Are Equal (arxiv.org)

Weakly supervised neural network: segmentation of complex structures in X-ray microCT (arxiv.org)

APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents (arxiv.org)

DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version (arxiv.org)

AAS-RAIL: Improving Information Extraction for Asset Administration Shells through Retrieval-Augmented In-Context Learning (arxiv.org)

Human-like moral judgments conceal divergent motive attributions in large language models (arxiv.org)

RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavioral Monitoring in Surveillance Systems (arxiv.org)

A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis (arxiv.org)

CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification (arxiv.org)

The Internal Anatomy of Strategic Choice in Large Language Models (arxiv.org)

Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Negation (arxiv.org)

Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Manufacturing Systems (arxiv.org)