SCULPT is a training-time method that enhances the readiness of edge vision models for low-bit post‑training quantization (PTQ). It introduces a topology‑aware activation regularizer to reduce skewness and kurtosis, and a stable percentile‑based clipping mechanism that learns deployment‑ready activation bounds during ordinary FP32 fine‑tuning. The resulting clipping bounds can be directly exported into standard PTQ workflows for INT8 or lower‑bit settings such as W4A8.
arXiv:2506.11784v2 Announce Type: replace Abstract: Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-wid...
VQ-Transplant is a framework that allows new vector‑quantization (VQ) modules to be inserted into frozen, pre‑trained visual tokenizers without retraining the entire model. By preserving all encoder‑decoder parameters and adding a lightweight decoder adaptation trained for only five epochs on ImageNet‑1k, the method mitigates decoder‑quantization mismatch. Experiments show that VQ-Transplant achieves near state‑of‑the‑art reconstruction fidelity for industry‑level models such as VAR while cutting training costs by 95%.
arXiv:2610.15297v1 Announce Type: cross Abstract: Recently, AutoRegressive Visual Generation (ARVG) models have emerged as a competitive paradigm for high-quality image synthesis. However, their subs...
arXiv:2609.16656v1 Announce Type: new Abstract: State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision...
The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.
arXiv:2510.04066v2 Announce Type: replace Abstract: Demoir\'eing aims to remove moir\'e artifacts that often occur in images. While recent deep learning-based methods have achieved promising results,...
arXiv:2611.08216v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. H...
State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision through ViM, VMamba, and Visual State Space Dual...
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...
arXiv:2607. 18540v1 Announce Type: cross Abstract: Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference.
Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. However, their substantial computational and memory...
arXiv:2510. 04547v5 Announce Type: replace Abstract: Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models.