Tag: deep learning
Browse our exclusive articles!
Volumetric Motion Fields for Radar Precipitation Nowcasting
Explore physics-informed deep learning to improve radar-based precipitation nowcasting using volumetric motion fields for enhanced weather forecasting accu...
Enhancing Harmonic Loss with Non-Euclidean Distance Metrics
Explore how non-Euclidean distance layers improve harmonic loss for better model accuracy, interpretability, and sustainability in deep learning.
AdaFRUGAL: Adaptive Memory-Efficient Training for LLMs
Discover AdaFRUGAL, an adaptive framework that optimizes LLM training with dynamic memory control, reducing GPU usage and boosting efficiency.
Consist-Retinex: Fast One-Step Retinex Low-Light Enhancement
Consist-Retinex delivers high-quality low-light image enhancement using one-step noise-emphasized training for fast, accurate Retinex-based restoration.
TinyR1-32B: Boost Accuracy with Branch-Merge Distillation
Discover how TinyR1-32B uses Branch-Merge Distillation to reduce LLM size while boosting accuracy in math, coding, and science benchmarks.