arXiv:2607. 28670v1 Announce Type: new Abstract: A stochastic Gumbel-Top-$K$ router defines, for every token of a mixture-of-experts (MoE) model, a \emph{routing law}: a distribution over ordered expert lists and mixture weights.
arXiv:2607. 28670v3 Announce Type: replace Abstract: A stochastic Gumbel-Top-K router defines, for every token of a mixture-of-experts (MoE) model, a routing law: a distribution over ordered expert lists and mixture weights.
arXiv:2606. 01509v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token.
arXiv:2608. 08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs.
arXiv:2607. 26052v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts $k$.
arXiv:2607. 28308v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions.
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions. Existing evidence often conflates route coherence, candidate quality, and candidate-by-context interaction.
arXiv:2608. 15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler gradient is blind to which wrong token receives probability mass.
arXiv:2512. 13996v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-$k$ routing imposes a rigid sparsity pattern that ignores the intrinsic variance in token difficulty and layer-specific computational needs.
arXiv:2607. 16246v1 Announce Type: cross Abstract: Off-policy distillation is now central to large language model pre-training, yet how training data, objective parameterization, and model capabilities interact remains poorly characterized.
arXiv:2606. 01007v1 Announce Type: cross Abstract: Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert communication and routing-induced load imbalance.
arXiv:2606. 18283v1 Announce Type: new Abstract: The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts.