Cluster 447399

JL-Cheng/SERE

[ICLR 2026] SERE: Similarity-Based Expert Re-routing for Efficient Batch Decoding in MoE Models

Jab1718/Moe-slices

No description

tianyi-lab/MoE-Embedding

[ICLR 2025 Oral] "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"

eelbaz/tensorbend-predictor

Cross-layer expert predictor for MoE models — predicts router expert selection before the gate runs