conftrace_

expert activation

5 papers

Explore in graph

Co-occurring keywords

mixture of expert (640) large language model (13587) parameter efficiency (417) language model (4599) representation learning (6206) expert specialization (26) multilingual model (925) knowledge retrieval (330) expert pruning (10) activation pattern (18)

Papers

CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices AAAI 2026
HMoE: Heterogeneous Mixture of Experts for Language Modeling EMNLP 2025
Multi-Head Mixture-of-Experts NIPS 2024
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs EMNLP 2024
Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications EMNLP 2024