arXiv:2607. 01444v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network must remain loaded.
arXiv:2609.30465v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models activate few experts per token but store the full expert pool. Expert pruning reduces this storage burden; at a fixed...
The paper introduces HOPE, a second‑order pruning method for Mixture‑of‑Experts language models that accounts for cooperative interactions between experts. Unlike first‑order methods such as REAP, HOPE derives an objective that provably bounds pruning error and is shown to outperform baselines across three large MoE models, multiple calibration sets, and diverse benchmarks, especially at high pruning rates and on agentic tasks. The results demonstrate that preserving expert interactions allows aggressive compression with minimal performance loss on complex workloads.
arXiv:2609.07803v1 Announce Type: new Abstract: Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performa...
arXiv:2606. 18304v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead.
Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing this parameter count,...
arXiv:2609.25809v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly man...
The paper examines how expert pruning—removing low‑importance experts in Mixture‑of‑Experts models—fails when the router is over‑dispersed, a condition caused by aggressive load‑balancing that spreads tokens nearly uniformly across experts. In this regime, traditional importance signals from router probabilities collapse, making perplexity an unreliable predictor of downstream accuracy; for example, the lowest‑perplexity pruning on gpt‑oss‑20B harms mathematical reasoning while the highest‑perplexity pruning preserves it. To address this, the authors introduce Minimax Expert Score Allocation (MESA), a domain‑aware method that iteratively boosts scores for the most affected domain, achieving minimal worst‑case degradation across domains and outperforming baseline pruning strategies on multiple benchmarks while reducing memory usage.
arXiv:2607. 16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token.
arXiv:2606. 15716v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation through sparse expert activation, yet deployment still requires storing the full expert pool, making one-shot expert pruning a practical approach for reducing memory usage.
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
arXiv:2608.29765v1 Announce Type: new Abstract: Structured pruning uses surrogate objectives because direct task evaluation over every feasible mask is too expensive. Most evaluations report average...
TAP-Path is a task‑adaptive compression framework that restructures a pretrained Virchow2 encoder for histopathology. It selectively removes transformer blocks, prunes patch tokens, and adds a lightweight gated task head, reducing parameters by 24.96% and FLOPs by 35.20% while maintaining high accuracy on a 32‑class benchmark. The method achieves competitive test metrics and improved rare‑class performance, with strong external validation on CPTAC samples.