SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness

• URL: http://arxiv.org/abs/2609.01743v1
• Date: Tue, 01 Sep 2026 18:10:19 GMT
• Title: SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness
• Abstract summary: Edge vision models are difficult to deploy on resource-constrained hardware.<n>We present SCULPT, a training-time method that improves PTQ readiness during ordinary FP32 fine-tuning.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Edge vision models are difficult to deploy on resource-constrained hardware, making low-bit post-training quantization (PTQ) attractive. In practice, standard FP32 training often produces heavy-tailed activation distributions whose outliers destabilize activation quantization: preserving the full range wastes quantization bins on rare extremes, while aggressive clipping causes information loss. Existing solutions typically rely on quantization-aware training (QAT), which adds training complexity and bit-width coupling, or advanced PTQ procedures that repair the model after training. We present SCULPT (Statistical Clipping and Uniform Loss for Post-Training), a training-time method that improves PTQ readiness during ordinary FP32 fine-tuning. SCULPT combines a topology-aware activation regularizer that suppresses quantization-hostile skewness and kurtosis with a stable percentile-based clipping mechanism that learns deployment-ready activation bounds. Unlike QAT, SCULPT does not simulate quantization during optimization; unlike post hoc outlier-repair PTQ methods, it does not require runtime activation transformations. The learned clipping bounds can be exported directly into a standard PTQ workflow for low-bit deployment, including INT8 and lower-bit settings such as W4A8.

Related papers

• ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization [10.647335642551193]
  Post-training quantization (PTQ) is widely used to reduce the computational cost of large language models.<n>We introduce ReQuant, a backpropagation-free fixed-grid refinement procedure for this stage.<n>We show that ReQuant consistently improves quantized models from heterogeneous PTQ initializers.
  arXiv  Detail & Related papers  (2026-08-07T09:27:14Z)
• ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers [60.09590321091875]
  Post-Training Quantization (PTQ) offers an attractive solution by compressing models using a small calibration set with minimal training overhead.<n>Most existing PTQ works adopt a static quantization paradigm that is uniformly applied to all instances.<n>We propose ScalePredictor, a dynamic quantization framework for accurate and efficient quantization scale learning of ViTs.
  arXiv  Detail & Related papers  (2026-06-20T08:33:55Z)
• Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin [13.185423069216808]
  Post-training quantization converts a trained full-precision model into low-bit weights without task-level retraining.<n>Although PTQ is efficient and often accurate at moderate bitwidths, it can fail sharply at aggressive bitwidths.<n>We propose a unified geometric framework that explains both PTQ failure and QAT recovery.
  arXiv  Detail & Related papers  (2026-06-08T04:21:39Z)
• Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay [9.836950534671775]
  Colinearity-Decay (CD) is a structural regularizer for ordered matrix pairs within Transformer blocks.<n>CD penalizes detrimental cross-matrix alignment and mitigates extreme activations without altering the architecture or task loss.
  arXiv  Detail & Related papers  (2026-05-02T08:49:51Z)
• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study [59.44848132298657]
  Post-training quantization (PTQ) usually comes with the cost of large accuracy drops, especially for reasoning tasks under low-bit settings.<n>In this study, we present a systematic empirical study of quantization-aware training (QAT) for reasoning models.
  arXiv  Detail & Related papers  (2026-01-21T11:22:29Z)
• PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models [29.616604431869746]
  Post-training quantization of large language models (LLMs) to extremely low bit-widths remains challenging.<n>Existing ultra-low-bit PTQ methods rely on binary approximations or complex compensation mechanisms.<n>We introduce PTQ to Trit-Planes (PTQTP), the first ternary-weight PTQ framework that decomposes weight matrices into structured ternary -1, 0, 1 trit-planes.
  arXiv  Detail & Related papers  (2025-09-21T09:07:20Z)
• End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost [53.25965863436039]
  Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs.<n>We propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization.<n>Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory.
  arXiv  Detail & Related papers  (2025-08-21T01:18:27Z)
• GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers [11.452135395287119]
  Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too.<n>Model quantization aims to alleviate this difficulty, yet existing Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) methods exhibit significant limitations.<n>This paper introduces General, Practical, and Quantization (GPLQ), a novel framework for efficient ViT quantization.
  arXiv  Detail & Related papers  (2025-06-13T13:45:17Z)
• APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers [71.2294205496784]
  We propose textbfAPHQ-ViT, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH)<n>We show that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks.
  arXiv  Detail & Related papers  (2025-04-03T11:48:56Z)
• Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization [62.15918574997175]
  It is known that language models contain outlier channels whose values on average are orders of magnitude higher than other channels. We propose a strategy which regularizes a layer's inputs via quantization-aware training (QAT) and its outputs via activation kurtosis regularization. We show that regularizing both the inputs and outputs is crucial for preventing a model's "migrating" the difficulty in input quantization to the weights.
  arXiv  Detail & Related papers  (2024-04-04T17:25:30Z)
• Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance [53.45700148820669]
  Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods.
  arXiv  Detail & Related papers  (2023-03-23T02:55:50Z)
• Towards Efficient Post-training Quantization of Pre-trained Language Models [85.68317334241287]
  We study post-training quantization(PTQ) of PLMs, and propose module-wise quantization error minimization(MREM), an efficient solution to mitigate these issues. Experiments on GLUE and SQuAD benchmarks show that our proposed PTQ solution not only performs close to QAT, but also enjoys significant reductions in training time, memory overhead, and data consumption.
  arXiv  Detail & Related papers  (2021-09-30T12:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.