Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly.
arXiv:2607. 28760v1 Announce Type: cross Abstract: As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality.
By Krunoslav Lehman Pavasovic, Th\'eophane Vallaeys, St\'ephane Mallat, Giulio Biroli, Luke Zettlemoyer, Brian Karrer, Jakob Verbeek
arXiv:2606. 02177v1 Announce Type: new Abstract: Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency.
By Francesco M. Ruscio, T. Konstantin Rusch
arXiv:2605. 26632v2 Announce Type: replace Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs.
By Xing Cong, Hanlin Tang, Kan Liu, Lan Tao, Lin Qu, Chenhao Xie
arXiv:2605. 26632v3 Announce Type: replace Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs.
By Xing Cong, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Chenhao Xie
arXiv:2605. 20708v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited.
By Chao Xu, Maohua Li, Qirui Li, Yixuan Xu, Yanke Zhou, Yunhe Li, Cuifeng Shen, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Shao-Qun Zhang