MATE is a multi-modal MoE trajectory policy using a cosine router and stochastic noise to improve expert balance, reporting 4.75% higher average success rate than prior methods on LIBERO under data scarcity.
Maskmoe: Boosting token-level learning via routing mask in mixture-of-experts.arXiv preprint arXiv:2407.09816
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
BEAM uses binary expert activation masks trained end-to-end to achieve dynamic sparsity in MoE models, cutting FLOPs by 85% with over 98% performance retention.
AIR-MoE introduces a two-stage inverted-index routing method based on vector quantization that approximates optimal expert selection for granular MoE models at lower cost and with empirical performance gains.
citing papers explorer
-
Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation
MATE is a multi-modal MoE trajectory policy using a cosine router and stochastic noise to improve expert balance, reporting 4.75% higher average success rate than prior methods on LIBERO under data scarcity.
-
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
BEAM uses binary expert activation masks trained end-to-end to achieve dynamic sparsity in MoE models, cutting FLOPs by 85% with over 98% performance retention.
-
Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
AIR-MoE introduces a two-stage inverted-index routing method based on vector quantization that approximates optimal expert selection for granular MoE models at lower cost and with empirical performance gains.