1. Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models
2. Scaling Adaptive Display Environments with On-Device Hybrid LLM-RAG Agents
3. Carbon- and System-Aware LoRA Scaling for On-Device LLMs via Hierarchical Multi-Objective Reinforcement Learning
4. Constraint-Aware Federated Learning: Multi-Resource Optimization via Dual Ascent
5. A Real-Time On-Device Defect Detection Framework for Laser Power-Meter Sensors via Unsupervised Learning
