mlsanityData to 14 Oct 2026

Beacon: Post-Training Quantization with Integrated Grid Selection

arXiv 2508.20293 ↗First posted 27 Aug 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Quantization is a widely used compression technique for reducing the memory and computation costs of large pre-trained models. A key challenge in per-channel post-training quantization (PTQ) is selecting appropriate scaling factors to replace weight values with values from a scaled integer grid. Existing methods typically fix the scale at the outset via heuristic tuning or grid search. We propose Beacon, a simple and effective algorithm that eliminates the need for such manual tuning. Beacon performs per-channel PTQ directly using an unscaled grid and automatically determines the optimal scaling factors by exploiting the geometry of scalar quantization. It does not rely on back-propagation or large calibration sets. Despite its simplicity and tuning-free nature, Beacon achieves competitive performance compared to state-of-the-art methods, making it a practical solution for efficient model deployment.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 27 Aug 2025.

Builds on

21 of 29 references.

References · 21

  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  2. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  4. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  7. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  8. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  9. 2022DeiT III: Revenge of the ViTcited by 419
  10. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  11. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  12. 2023Training Transformers with 4-bit Integerscited by 60
9 more
  1. 2023Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMscited by 50
  2. 2022Post-training Quantization for Neural Networks with Provable Guaranteescited by 33
  3. 2024LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkitcited by 33
  4. 2024MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantizationcited by 28
  5. 2025Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantizationcited by 28
  6. 2020A Greedy Algorithm for Quantizing Neural Networkscited by 22
  7. 2025Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronoscited by 16
  8. 2024COMQ: A Backpropagation-Free Algorithm for Post-Training Quantizationcited by 12
  9. 2025Theoretical Guarantees for Low-Rank Compression of Deep Neural Networkscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Optimal Post-Training Quantization Scales and Where to Find Themcited by 3
  2. 2026GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptationcited by 1
  3. 2026Signed Symmetric Quantization for Few-Bit Integerscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
  2. 2026Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape
  3. 2026Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
  4. 2023Gradient-Based Post-Training Quantization: Challenging the Status Quo
  5. 2025Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
  6. 2026The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization
  7. 2025Improving Quantization with Post-Training Model Expansion
  8. 2026C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs