mixture-of-experts 5
- LLM Inference Parallelism Is a Rank-Topology Problem
- Qwen3-Coder-Next: Hybrid Mixture-of-Experts and Agentic Reinforcement Learning
- Mixture-of-Experts Architecture: From Sparse Routing to Fine-Grained LLaMA 4 Scaling
- Frontier LLM Research Trends: Test-Time Compute, State-Space Models, and MoE
- Uni-MoE Architecture: Unified Multimodal MoE and Three-Stage Modality Alignment