RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
arXiv:2609.25492v1 Announce Type: new Abstract: Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ methods are designed for unimodal large language models (LLMs). These methods tr…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-23 04:00 · arXiv cs.CV
RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models