Beyond Reconstruction Loss in Post-Training Quantization: Balanced Fitting for Large Vision-Language Models
cs.CV, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/kmc3661/BFQ
Terminology
Sources
- Token Merging: Your ViT But Faster
- Microsoft COCO Captions: Data Collection and Evaluation Server
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Distilling the Knowledge in a Neural Network
- LLaVA-OneVision: Easy Visual Task Transfer
- FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
- LLaMA: Open and Efficient Foundation Language Models
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
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