arXiv AI
Jun 2
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
arXiv:2606. 01509v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token.
Towards a Statistical Understanding of Mixture-of-Experts
The paper presents a statistical framework for Mixture-of-Experts (MoE) models, treating them as localized aggregation systems. It derives oracle risk bounds that separate approximation, expert‑learning, and router‑estimation errors for both dense and sparse routing with evolving experts. The authors also analyze how sparse Top‑K routing balances computational cost with performance, interpret gating geometrically, and explain how shared experts can capture common predictive structure while allowing routed experts to focus on local residuals.
Related stories
arXiv Machine Learning
Aug 12
Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
arXiv AI
Sep 17
MoRE: Mixture of Reused Experts
MoRE: Mixture of Reused Experts is a hybrid architecture that combines Mixture-of-Experts (MoE) with weight‑sharing techniques. It shares expert pools across adjacent layers while each layer keeps its own router, and introduces lightweight depth embeddings to help shared experts differentiate layer contexts. Experiments on models ranging from 114 M to 1.15 B parameters show MoRE achieves lower perplexity and better downstream performance than standard MoEs and other weight‑sharing models, with only minimal changes to existing MoE implementations.
arXiv AI
Jun 3
DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
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 AI
Sep 3
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
The paper investigates how routing decisions in sparse mixture-of-experts (MoE) models evolve across layers. By aligning router control subspaces with generalized orthogonal Procrustes analysis, the authors find that a single linear transition can predict routing states across depth with substantial accuracy, revealing a shared geometric structure. They further demonstrate that these canonical states preserve expert selection better than generic hidden representations and improve next‑step routing predictions, reducing negative log‑likelihood by up to 15.7% on OLMoE and 6.2% on Phi.
arXiv AI
Jun 17
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
arXiv:2606. 17952v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top-$k$ routing.
arXiv Machine Learning
Jun 17
MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
arXiv:2602. 06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.
arXiv Machine Learning
Aug 6
Elbow-Based MoE Routing: A Training-Free Inference Time Plugin for Expert Selection
arXiv:2608. 04401v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable model scaling while maintaining low inference-time compute by activating only a subset of experts per token.
arXiv Computation and Language
Sep 10
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts
arXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large f...
arXiv Computation and Language
Aug 28
Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs
MetaNet is a support‑set controller that predicts, for each layer of a Mixture‑of‑Experts model, an expert‑retention threshold and a bounded routing bias while keeping the backbone, experts, and router frozen. On DeepSeek‑MoE‑16B‑Chat, MetaNet offers a tunable trade‑off between accuracy and expert activation: a conservative setting activates 3.61 experts on average (40% fewer than a fixed k=6) with comparable MMLU accuracy, whereas an aggressive setting activates only 2.28 experts (62% fewer) with a modest accuracy drop. The MMLU‑trained controller also transfers to C‑Eval, activating 2.90 experts on average (52% fewer than fixed k=6) at 0.386 accuracy.
arXiv Computation and Language
Sep 10
Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning
arXiv:2604.23036v2 Announce Type: replace-cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...
arXiv AI
Jun 2
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
arXiv:2606. 01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge.