# AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models

arXiv: https://arxiv.org/abs/2406.13233 · HTML: https://mlsanity.com/paper/2406.13233/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts](https://mlsanity.com/paper/2404.15159/) (2024)
- [When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications](https://mlsanity.com/paper/2310.18339/) (2023)
- [Higher Layers Need More LoRA Experts](https://mlsanity.com/paper/2402.08562/) (2024)
- [LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin](https://mlsanity.com/paper/2312.09979/) (2023)
- [SocialIQA: Commonsense Reasoning about Social Interactions](https://mlsanity.com/paper/1904.09728/) (2019)
- [Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models](https://mlsanity.com/paper/2203.03131/) (2022)

## Built on by (most cited first, 30 of 44)

- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [LongCat-Flash Technical Report](https://mlsanity.com/paper/2509.01322/) (2025)
- [MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts](https://mlsanity.com/paper/2410.07348/) (2024)
- [Advancing Expert Specialization for Better MoE](https://mlsanity.com/paper/2505.22323/) (2025)
- [SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations](https://mlsanity.com/paper/2512.14080/) (2025)
- [TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding](https://mlsanity.com/paper/2508.01699/) (2025)
- [LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts](https://mlsanity.com/paper/2509.25684/) (2025)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism](https://mlsanity.com/paper/2504.00661/) (2025)
- [Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts](https://mlsanity.com/paper/2509.21892/) (2025)
- [Faster MoE LLM Inference for Extremely Large Models](https://mlsanity.com/paper/2505.03531/) (2025)
- [Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts](https://mlsanity.com/paper/2508.07785/) (2025)
- [Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models](https://mlsanity.com/paper/2509.25826/) (2025)
- [MoE Pathfinder: Trajectory-driven Expert Pruning](https://mlsanity.com/paper/2512.18425/) (2025)
- [LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2411.00918/) (2024)
- [ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference](https://mlsanity.com/paper/2510.26730/) (2025)
- [φ-Balancing for Mixture-of-Experts Training](https://mlsanity.com/paper/2605.15403/) (2026)
- [A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design](https://mlsanity.com/paper/2607.09084/) (2026)
- [LaDiMo: Layer-wise Distillation Inspired MoEfier](https://mlsanity.com/paper/2408.04278/) (2024)
- [Glider: Global and Local Instruction-Driven Expert Router](https://mlsanity.com/paper/2410.07172/) (2024)
- [Post-Trained MoE Can Skip Half Experts via Self-Distillation](https://mlsanity.com/paper/2605.18643/) (2026)
- [RANGER: Sparsely-Gated Mixture-of-Experts with Adaptive Retrieval Re-ranking for Pathology Report Generation](https://mlsanity.com/paper/2603.04348/) (2026)
- [Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing](https://mlsanity.com/paper/2603.11535/) (2026)
- [DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models](https://mlsanity.com/paper/2410.01497/) (2024)
- [Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning](https://mlsanity.com/paper/2502.03884/) (2025)
- [THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation](https://mlsanity.com/paper/2505.14173/) (2025)
- [GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models](https://mlsanity.com/paper/2510.13079/) (2025)
- [T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic Routing](https://mlsanity.com/paper/2609.15160/) (2026)
- [Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling](https://mlsanity.com/paper/2509.00679/) (2025)
- [Improving MoE Compute Efficiency by Composing Weight and Data Sparsity](https://mlsanity.com/paper/2601.15370/) (2026)

## Abstract (arXiv)

Mixture of experts (MoE) has become the standard for constructing production-level large language models (LLMs) due to its promise to boost model capacity without causing significant overheads. Nevertheless, existing MoE methods usually enforce a constant top-k routing for all tokens, which is arguably restrictive because various tokens (e.g., "<EOS>" vs. "apple") may require various numbers of experts for feature abstraction. Lifting such a constraint can help make the most of limited resources and unleash the potential of the model for downstream tasks. In this sense, we introduce AdaMoE to realize token-adaptive routing for MoE, where different tokens are permitted to select a various number of experts. AdaMoE makes minimal modifications to the vanilla MoE with top-k routing -- it simply introduces a fixed number of null experts, which do not consume any FLOPs, to the expert set and increases the value of k. AdaMoE does not force each token to occupy a fixed number of null experts but ensures the average usage of the null experts with a load-balancing loss, leading to an adaptive number of null/true experts used by each token. AdaMoE exhibits a strong resemblance to MoEs with expert choice routing while allowing for trivial auto-regressive modeling. AdaMoE is easy to implement and can be effectively applied to pre-trained (MoE-)LLMs. Extensive studies show that AdaMoE can reduce average expert load (FLOPs) while achieving superior performance. For example, on the ARC-C dataset, applying our method to fine-tuning Mixtral-8x7B can reduce FLOPs by 14.5% while increasing accuracy by 1.69%.