arXiv Computer Vision By Xianghong Fang, Yuan Yuan, Dehan Kong, Tim G. J. Rudner

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

Read the original on arXiv Computer Vision →

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%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
Sep 3

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

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.

By Bharadwaj Kavuri, Sourav Babu-PK, Varadhraj Ellapan, Pullarao Maddu, Prasad Deshpande
arXiv AI
Jul 29

Argus-Unified: Towards A Compact and Economical Unified Model for Image Understanding and Generation

arXiv:2607. 25527v1 Announce Type: cross Abstract: Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities.

By Weiming Zhuang, Jiabo Huang, Jingtao Li, Zhizhong Li, Chen Chen, Sina Sajadmanesh, Lingjuan Lyu