SHAPE: New Method for Pruning Mixture-of-Experts Language Models Using Coalition-Aware Expert Scoring
Researchers have developed SHAPE, a new framework for removing redundant experts from sparse Mixture-of-Experts (MoE) large language models while maintaining performance. The method uses game theory concepts to identify which experts work together effectively, rather than scoring them independently. This addresses a key deployment challenge where keeping all experts in memory limits practical use of these efficient models.
SHAPE is a pruning framework designed to reduce memory requirements for deploying sparse MoE language models by identifying and removing less critical experts. Unlike prior approaches that evaluate experts individually, SHAPE models how experts collaborate by treating routing patterns as a cooperative game and assigning importance scores based on expert interactions within top-k combinations. The framework includes a quality-coverage selection rule that preserves model topology by retaining the minimal expert subset in each layer needed to maintain performance. Testing on three modern MoE models (Qwen3-30B-A3B, GPT-OSS-20B, and DeepSeek-V2-Lite) demonstrated that SHAPE maintains competitive accuracy when removing 20-40% of experts without additional training, while reducing peak GPU memory usage. The authors have released open-source code for the method.
What's missing
The paper does not discuss potential limitations of the Shapley value approach for very large expert pools, computational overhead of the pruning process itself, or how performance scales with different calibration set sizes.
What different sources said
- arXiv cs.LGCenter
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.