| From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models | cs.AI | 0 | Open |
| Usable Agent Discovery for Decentralized AI Systems | cs.AI | 0 | Open |
| Code Broker: A Multi-Agent System for Automated Code Quality Assessment | cs.AI | 0 | Open |
| Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach | cs.AI | 0 | Open |
| ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation | cs.AI | 0 | Open |
| No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows | cs.AI | 0 | Open |
| Mixture of Heterogeneous Grouped Experts for Language Modeling | cs.AI | 0 | Open |
| ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation | cs.AI | 0 | Open |
| MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration | cs.AI | 0 | Open |
| Mechanistic Steering of LLMs Reveals Layer-wise Feature Vulnerabilities in Adversarial Settings | cs.AI | 0 | Open |
| CNN-ViT Fusion with Adaptive Attention Gate for Brain Tumor MRI Classification: A Hybrid Deep Learning Model | cs.AI | 0 | Open |
| UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks | cs.AI | 0 | Open |
| UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks | cs.AI | 0 | Open |
| PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks | cs.AI | 0 | Open |
| Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns | cs.AI | 0 | Open |