RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference Paper • 2603.17891 • Published 6 days ago • 7
RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference Paper • 2603.17891 • Published 6 days ago • 7
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation Paper • 2507.06013 • Published Jul 8, 2025