The paper introduces Multi-View Latent MoE, a sparse mixture‑of‑experts architecture that uses multiple independent routers to generate richer selection signals and to modulate expert computation. By aggregating sigmoid scores from these routers, the model selects experts that are strongly favored by one or several routers and mixes their relative scores into each expert’s input, thereby reusing routing preferences for both selection and computation. Experiments on a 24‑layer 10B‑A1B model trained on 708 B tokens show a 1.18‑point improvement in nine‑task downstream mean over the baseline, with the Multi‑Router submodule alone providing a 0.6‑point gain and significantly better alignment between router scores and expert utility. whyItMatters":"The approach demonstrates that leveraging multiple routers can both improve expert selection quality and maintain computational efficiency, leading to measurable downstream performance gains on large‑scale language models."
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
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.
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.
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.
MASKerade is a new dense‑to‑MoE training method that learns experts as sparse subnetworks of a frozen pretrained feed‑forward network (FFN) using binary masks. A token‑level router selects which masked FFNs to execute, and both the router and mask scores are jointly optimized while the underlying FFN weights remain unchanged. In experiments on five vision‑language benchmarks with Qwen and Gemma backbones, a configuration of four 2:4 experts with top‑2 routing achieved the best performance among compared baselines, demonstrating that mask learning over frozen weights is a practical alternative for constructing token‑routed MoE experts.
IntBMoE introduces a block‑conditioned mixture‑of‑experts that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. Each internal layer uses a lightweight hypernetwork to merge all expert bases into a single composed expert, while a router selects only a few blocks per token, keeping compute and memory costs low. Experiments on image classification, language modeling, and sequential recommendation demonstrate consistent performance gains, and the model is deployed in AMap’s generative recommendation system, improving UVCTR by 2.4% in online A/B tests.
GaP-MoE introduces a method for explicit expert specialization in Sparse Mixture-of-Experts models by manipulating expert output gradients instead of adding auxiliary loss terms. The technique selects a leader expert from the top‑K routed experts and projects follower experts’ gradients onto the orthogonal complement of the leader’s recent gradients, reducing directional overlap. Experiments on fine‑tuning BERT for GLUE and pretraining GPT‑2 on various corpora show that GaP‑MoE matches or surpasses standard SMoE performance while remaining a drop‑in module.
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:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
MoRA is a framework for pruning Mixture-of-Experts (MoE) models by learning a router bias for each expert and optimizing it with a language‑modeling loss and a routing‑diversity regularizer. The learned biases sharpen routing distributions to identify critical experts and encourage diverse routing preferences. After pruning, MoRA uses an expert approximation mechanism that approximates the outputs of pruned experts with affine transformations of remaining experts, further improving performance.
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:2607. 26618v1 Announce Type: new Abstract: Federated PEFT enables LLMs to collaboratively adapt to decentralized private data without sharing raw examples.