PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers

arXiv:2609.33384 · cs.CV · Submitted 2026-09-27 · Read on arXiv

cs.CV

Submitted: 2026-09-27

Updated: 2026-09-29

Code: https://github.com/hhhh1138/PulseQuant

Terminology

• Calibration — 64× in this paper · explained in 7 episodes
• Quantization — 48× in this paper · explained in 12 episodes
• Fidelity — 23× in this paper · explained in 2 episodes
• Transformer — 16× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Diffusion Model — 10× in this paper · explained in 8 episodes
• Diffusion Models — 10× in this paper · explained in 6 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Adaptation — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Elias — 2× in this paper · explained in 2 episodes
• Error Decomposition — 2× in this paper · explained in 3 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 1× in this paper
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Drift — 1× in this paper · explained in 3 episodes

Sources

• Extreme Compression of Large Language Models via Additive Quantization
• Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
• Wan: Open and Advanced Large-Scale Video Generative Models
• SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
• ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

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