HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models
cs.CV, cs.AI
Submitted: 2026-10-11
Updated: 2026-10-11
Terminology
Sources
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
- ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
- FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
- Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
- SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- DVD-Quant: Data-free Video Diffusion Transformers Quantization
- Microsoft COCO: Common Objects in Context
- Improved Techniques for Training GANs
- OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
- Parallelized Autoregressive Visual Generation
- FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design
- Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling
- LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
- Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
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