# Mixture of Lookup Experts

arXiv: https://arxiv.org/abs/2503.15798 · HTML: https://mlsanity.com/paper/2503.15798/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 22 of 22)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [Distributed Gaussian Processes](https://mlsanity.com/paper/1502.02843/) (2015)
- [MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts](https://mlsanity.com/paper/2410.07348/) (2024)
- [Generative Image Modeling Using Spatial LSTMs](https://mlsanity.com/paper/1506.03478/) (2015)

## Built on by (most cited first, 12 of 12)

- [MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers](https://mlsanity.com/paper/2602.00398/) (2026)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory](https://mlsanity.com/paper/2605.20948/) (2026)
- [Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression](https://mlsanity.com/paper/2510.02345/) (2025)
- [JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation](https://mlsanity.com/paper/2602.00800/) (2026)
- [Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts](https://mlsanity.com/paper/2602.03473/) (2026)
- [Mixture of Lookup Key-Value Experts](https://mlsanity.com/paper/2512.09723/) (2025)
- [Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling](https://mlsanity.com/paper/2604.13508/) (2026)
- [TIDE: Every Layer Knows the Token Beneath the Context](https://mlsanity.com/paper/2605.06216/) (2026)
- [Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence](https://mlsanity.com/paper/2607.20981/) (2026)
- [Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding](https://mlsanity.com/paper/2609.04238/) (2026)
- [ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models](https://mlsanity.com/paper/2610.01296/) (2026)

## Abstract (arXiv)

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the experts need to be loaded into VRAM. Their large parameter size still limits deployment, and offloading, which load experts into VRAM only when needed, significantly increase inference latency. To address this, we propose Mixture of Lookup Experts (MoLE), a new MoE architecture that is efficient in both communication and VRAM usage. In MoLE, the experts are Feed-Forward Networks (FFNs) during training, taking the output of the embedding layer as input. Before inference, these experts can be re-parameterized as lookup tables (LUTs) that retrieves expert outputs based on input ids, and offloaded to storage devices. Therefore, we do not need to perform expert computations during inference. Instead, we directly retrieve the expert's computation results based on input ids and load them into VRAM, and thus the resulting communication overhead is negligible. Experiments show that, with the same FLOPs and VRAM usage, MoLE achieves inference speeds comparable to dense models and significantly faster than MoE with experts offloading, while maintaining performance on par with MoE.