pith. sign in

Competesmoe--effective training of sparse mixture of experts via competition

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

years

2026 2 2025 1

verdicts

UNVERDICTED 3

clear filters

representative citing papers

Tight Clusters Make Specialized Experts

cs.LG · 2025-02-21 · unverdicted · novelty 6.0

Introduces Adaptive Clustering router for MoE models that scales features to identify tight expert clusters, yielding faster convergence, robustness to corruption, and performance gains.

Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models

cs.LG · 2026-06-30 · unverdicted · novelty 5.0

Mixture-of-Control adaptively combines local and global control states in transformer fine-tuning by treating per-block states as experts in a sparse MoE setup to improve cross-block communication while keeping memory and compute costs comparable to prior state-based methods.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Tight Clusters Make Specialized Experts cs.LG · 2025-02-21 · unverdicted · none · ref 35

    Introduces Adaptive Clustering router for MoE models that scales features to identify tight expert clusters, yielding faster convergence, robustness to corruption, and performance gains.