arXiv Computer Vision
PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 3
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
arXiv:2607. 02461v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive.
arXiv Computer Vision
Sep 4
DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
The paper introduces DSAQuant, a quantization‑aware training framework tailored for video diffusion models (VDMs). It aligns quantization with the denoising stages of VDMs, using denoising‑stage‑oriented supervision during training and denoising‑stage gated guidance during inference to preserve structure while improving detail reconstruction. Experiments on Wan and CogVideoX models under aggressive W3A3 and W4A4 quantization settings show that DSAQuant outperforms state‑of‑the‑art QAT baselines, boosting VBench scores by up to 6.60 while maintaining strong text‑video alignment.
arXiv Machine Learning
Aug 12
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
arXiv:2608. 11045v1 Announce Type: new Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals.
arXiv Computer Vision
Sep 21
Quantization-Aware Kalman Estimation for Diffusion Sampling
The paper introduces QuAKE, a Quantization-Aware Kalman Estimator designed to correct errors in diffusion model sampling when using quantized denoisers. By treating sampling as an online estimation problem, QuAKE leverages the history of quantized outputs to recover full-precision estimates, updating a posterior in closed form at each step. The method is lightweight, plug‑and‑play, and works with any high‑order multistep ODE sampler, outperforming existing correction techniques on W4A4‑quantized text‑to‑image diffusion models.
Hugging Face Trending Papers
5d ago
FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Diffusion-based video restoration recovers realistic details, but its practical deployment is limited by two efficiency bottlenecks: costly VAE encoding and decoding, and the quadratic cost of full se...
arXiv Machine Learning
Aug 17
Post-training Quantization for Hybrid Iterative Generative Models
arXiv:2608. 13932v1 Announce Type: new Abstract: Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity.