Technology ❯ Computer Science ❯ Artificial Intelligence

Deep Learning

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