arXiv:2606. 01666v1 Announce Type: cross Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency.
arXiv:2511. 08972v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) models are scalable and computationally efficient, enabling large increases in model capacity with limited inference overhead.
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: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: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:2606. 01509v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token.
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.
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.
The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
arXiv:2608. 03457v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood.
PCoMoE introduces a path‑compositional execution framework that moves Mixture‑of‑Experts inference from coarse‑grained expert selection to fine‑grained path composition. It uses a path‑level formulation of expert computation, a compatibility‑aware layer‑wise pruning strategy to eliminate low‑value path combinations, and a hardware‑friendly execution engine that reuses sub‑expert structures with bounded overhead. Experiments show up to a 1.31× speedup and a 10% accuracy improvement over existing MoE inference methods.
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:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.