mlsanityData to 7 Oct 2026

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

arXiv 1712.05877 ↗First posted 15 Dec 2017cs.LG stat.MLcited by 1,548

Not on the map. Why?

Cited by 50 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficiently than floating point inference on commonly available integer-only hardware. We also co-design a training procedure to preserve end-to-end model accuracy post quantization. As a result, the proposed quantization scheme improves the tradeoff between accuracy and on-device latency. The improvements are significant even on MobileNets, a model family known for run-time efficiency, and are demonstrated in ImageNet classification and COCO detection on popular CPUs.

Key facts. Cited by 1,548 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 232; 2022: 202; 2023: 201; 2024: 277; 2025: 319; 2026: 317.

1,548 papers.

Sort:

By area:

  1. 2025Gemma 3 Technical Reportcited by 1,686
  2. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  3. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  4. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 805
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  6. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  7. 2021A White Paper on Neural Network Quantizationcited by 453
  8. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  9. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 320
  10. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  11. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  12. 2022Post-training Quantization on Diffusion Modelscited by 262
38 more
  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  3. 2021NeRV: Neural Representations for Videoscited by 255
  4. 2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 255
  5. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  6. 2022The case for 4-bit precision: k-bit Inference Scaling Lawscited by 247
  7. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 247
  8. 2021COIN: COmpression with Implicit Neural representationscited by 232
  9. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 232
  10. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 232
  11. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  12. 2026Gemma 4 Technical Reportcited by 187
  13. 2021Learning N:M Fine-grained Structured Sparse Neural Networks From Scratchcited by 177
  14. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  15. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  16. 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMscited by 165
  17. 2022On-Device Training Under 256KB Memorycited by 158
  18. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
  19. 2024GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMcited by 155
  20. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  21. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  22. 2023Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothingcited by 147
  23. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  24. 2021Understanding and Overcoming the Challenges of Efficient Transformer Quantizationcited by 139
  25. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 137
  26. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  27. 2025EmbeddingGemma: Powerful and Lightweight Text Representationscited by 128
  28. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 127
  29. 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computationcited by 120
  30. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  31. 2024FlatQuant: Flatness Matters for LLM Quantizationcited by 116
  32. 2022The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Modelscited by 115
  33. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  34. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 110
  35. 2024Sequoia: Scalable, Robust, and Hardware-aware Speculative Decodingcited by 103
  36. 2023HNeRV: A Hybrid Neural Representation for Videoscited by 100
  37. 2026Kimi K3: Open Frontier Intelligencecited by 99
  38. 2022LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Modelscited by 98

50 most cited of 1,548 All 1,548 (JSON)