Technology ❯ Computer Science ❯ Artificial Intelligence

Deep Learning

Neural Networks Transformers Model Optimization Mixture-of-Experts Large Language Models Vision Transformers Convolutional Neural Networks Loss Functions Parameter-Efficient Fine-Tuning GNN Architecture Transfer Learning Attention Mechanisms Implicit Neural Representations Cascaded Frameworks Neural Network Architectures Network Architectures Feature Learning Parameter Efficiency Training Techniques Pre-trained Models Progressive Learning Zero-shot Learning Model Training Image Classification Model Training Techniques LSTM Models Sparse Autoencoders Fine-Tuning Techniques Feature Evolution Model Evaluation

MoE Research Delivers New Playbooks for Design, Routing, and Real-World Deployment

The releases point to simpler design rules with practical fixes that make sparse expert models easier to scale.

HI-MoE Proposes Two-Stage Expert Routing for Object Detection

DeepSeek Publishes mHC to Stabilize Wider Residual Streams in LLMs