mlsanityData to 14 Oct 2026

LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup

arXiv 2302.03213 ↗First posted 7 Feb 2023cs.LG cs.NEcited by 20

Not on the map. Why?

Abstract (arXiv)

On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower inference by table lookup, to reduce inference cost. LUT-NN learns the typical features for each operator, named centroid, and precompute the results for these centroids to save in lookup tables. During inference, the results of the closest centroids with the inputs can be read directly from the table, as the approximated outputs without computations. LUT-NN integrates two major novel techniques: (1) differentiable centroid learning through backpropagation, which adapts three levels of approximation to minimize the accuracy impact by centroids; (2) table lookup inference execution, which comprehensively considers different levels of parallelism, memory access reduction, and dedicated hardware units for optimal performance. LUT-NN is evaluated on multiple real tasks, covering image and speech recognition, and nature language processing. Compared to related work, LUT-NN improves accuracy by 66% to 92%, achieving similar level with the original models. LUT-NN reduces the cost at all dimensions, including FLOPs (≤ 16x), model size (≤ 7x), latency (≤ 6.8x), memory (≤ 6.5x), and power (≤ 41.7%).

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

32 of 62 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  6. 2020Knowledge Distillation: A Surveycited by 1,603
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  8. 2020Designing Network Design Spacescited by 960
  9. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  10. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  11. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  12. 2020What is the State of Neural Network Pruning?cited by 583
20 more
  1. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  2. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  3. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  4. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  5. 2013Predicting Parameters in Deep Learningcited by 224
  6. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 195
  7. 2019And the Bit Goes Down: Revisiting the Quantization of Neural Networkscited by 78
  8. 2020LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applicationscited by 57
  9. 2022ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantizationcited by 51
  10. 2019Differentiable Product Quantization for End-to-End Embedding Compressioncited by 36
  11. 2016Ternary Neural Networks for Resource-Efficient AI Applicationscited by 33
  12. 2018Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inferencecited by 33
  13. 2021Multiplying Matrices Without Multiplyingcited by 30
  14. 2015Quantization based Fast Inner Product Searchcited by 29
  15. 2017SUBIC: A supervised, structured binary code for image searchcited by 12
  16. 2016LCNN: Lookup-based Convolutional Neural Networkcited by 11
  17. 2018Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Visioncited by 10
  18. 2017Bolt: Accelerated Data Mining with Fast Vector Compressioncited by 7
  19. 2021Boosting Mobile CNN Inference through Semantic Memorycited by 6
  20. 2022Look-ups are not (yet) all you need for deep learning inferencecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 8; 2026: 5.

20 papers.

Sort:

By area:

  1. 2024GPTVQ: The Blessing of Dimensionality for LLM Quantizationcited by 82
  2. 2024T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edgecited by 55
  3. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  4. 2025Bitnet.cpp: Efficient Edge Inference for Ternary LLMscited by 22
  5. 2025LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Acceleratorcited by 9
  6. 2024Anatomizing Deep Learning Inference in Web Browserscited by 6
  7. 2025LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAscited by 4
  8. 2025LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neuronscited by 3
  9. 2023Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplicationcited by 1
  10. 2024AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environmentscited by 1
  11. 2025VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolutioncited by 1
  12. 2025LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillationcited by 1
8 more
  1. 2025Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Modelscited by 1
  2. 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIMcited by 1
  3. 2026FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compressioncited by 1
  4. 2026Breaking the 1.58-bit Barrier for Ternary LLMscited by 1
  5. 2024Mitigating scalability challenges in LUT-based neural networks via pruning optimisationscited by 0
  6. 2025Synera: Synergistic LLM Serving across Device and Cloud at Scalecited by 0
  7. 2026Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequencescited by 0
  8. 2026FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergycited by 0