Co-occurring keywords · papers mentioning both
Papers
Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts
AAAI 2026
DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
CVPR 2025
Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
ICLR 2025
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Experts
EMNLP 2025
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints
ICLR 2023