RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
cs.CV, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Code: https://github.com/EvolvingLMMs-Lab/lmms-eval
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- SpinQuant: LLM quantization with learned rotations
- FlatQuant: Flatness Matters for LLM Quantization
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
- LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
- OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- LLaVA-OneVision: Easy Visual Task Transfer
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models