Challenge: Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE architectures.
Approach: They propose to analyze sparse MoE architectures against dense models to capture dynamic routing-expert interactions.
Outcome: The proposed algorithm shows that sparse models achieve higher efficiency per layer . it also shows that deep Qwen-MoE mitigates expert failures while minimizing complexity .

Similar Papers

Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on isolated aspects of MoE, with conflicting conclusions . a lack of consensus on optimal design choices is limiting to specific aspects of the model.
Approach: They propose to evaluate two popular MoE backbones across four dimensions of design choices . they find token-level routing and z-loss regularization improve reasoning performance .
Outcome: The proposed framework evaluates two popular MoE backbones on over eight metrics.
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference (2021.findings-emnlp)

Copied to clipboard

Challenge: Sparse Mixture-of-Experts (MoE) is a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation.
Approach: They propose to use a task-level routing approach to extract smaller, ready-to-deploy sub-networks from large sparse models by ignoring distillation.
Outcome: Experiments on WMT and a web-scale dataset show that task-level routing outperforms token-level MoE models by +1.0 BLEU on average across 30 language pairs.
A Closer Look into Mixture-of-Experts in Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Mixture-of-experts (MoE) architectures are gaining increasing attention for their unique properties and remarkable performance.
Approach: They propose a mixture-of-experts architecture that allows for model scaling without sacrificing computational efficiency.
Outcome: The proposed model increases model size without sacrificing computational efficiency . the proposed model is modular and can be used by a broad spectrum of practitioners .
CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, mixture-of-experts (MoE) is underutilized on heterogeneous datasets, ignoring the fact that experts may learn similar knowledge.
Approach: They propose a method to promote modularization and specialization in MoE by specializing functionalities into different experts and sparsely activating them appropriately.
Outcome: The proposed method improves the capacity and specialization of mixture-of-experts (MoE) by sampling from activated and inactivated experts in top-k routing.
Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have outstanding performance by learning a large number of model parameters on large amounts of data.
Approach: They propose a method of grouping and pruning similar experts to improve the model’s parameter efficiency by a range of natural language tasks.
Outcome: The proposed method outperforms other model pruning methods on a range of natural language tasks.
Faster MoE LLM Inference for Extremely Large Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing inference optimizations for coarse-grained Mixture-of-Experts models implicitly assume a fixed activation budget, which is poorly understood.
Approach: They propose a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget.
Outcome: The proposed skipping policy can provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms.
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches that reduce expert activations lead to severe model performance degradation.
Approach: They propose a framework that optimizes budget allocation coordinately at layer and token levels to minimize model performance degradation.
Outcome: The proposed framework achieves 1.15 prefill and 1.34 decode speedups on DeepSeek-V2-Lite at half of the original budget.
Specialization through Collaboration: Understanding Expert Interaction in Mixture-of-Expert Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) based large language models are popular for multitasking . however, whether each expert can specialize to a task remains unclear .
Approach: They propose to use a dictionary learning approach to analyze expert collaboration mechanisms in MoE LLMs.
Outcome: The proposed model outperforms existing methods by 2.5% while enabling 50% expert reduction.
Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Challenge: A sparse Mixture-of-Experts architecture has emerged as a highly scalable solution for instruction tuning.
Approach: They propose a mixture-of-Clustered-Experts (MoCE) architecture that allows expert specialization . they evaluate the mechanism on a set of benchmarks and show its superiority .
Outcome: The proposed approach outperforms existing models and benchmarks on instruction tuning scenarios with significant input heterogeneity.
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs.
Approach: They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them.
Outcome: The proposed architecture achieves comparable performance with GShard with 2B parameters and computation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations