Technology ❯ Artificial Intelligence ❯ Model Architecture

Mixture-of-Experts

Efficiency Parameter Efficiency Parameter Activation Multimodal Models Efficiency Optimization DeepSeek-V3 Hybrid Latent MoE DeepSeek V3 Parameter Optimization Performance Benchmarking

3 ARTICLES

last mo.

Nvidia Unveils Nemotron 3 Ultra, a 550B Open-Weight AI Model

Publishing weights and training recipes, Nvidia aims to cut inference costs and speed research by using a mixture-of-experts design with NVFP4-driven throughput gains.

4 ARTICLES

8mo ago

Moonshot AI Releases Open-Source Kimi K2 Thinking, a Tool-Using 'Thinking Agent'

7 ARTICLES

last yr.

Alibaba Elevates Qwen3 Open-Source AI with Benchmark-Topping Upgrades

7 ARTICLES

last yr.

DeepSeek V3 Challenges AI Giants With Open-Source Model and Efficiency Breakthroughs