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.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.33384v2 Announce Type: replace Abstract: Quantization errors in video diffusion transformers can be amplified or attenuated by subsequent denoising updates, making local reconstruction err...
arXiv:2607. 21446v1 Announce Type: new Abstract: Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent.
arXiv:2607. 03803v1 Announce Type: cross Abstract: The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc.
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:2606. 00094v1 Announce Type: cross Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterization space.
arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.