APEX (Asynchronous Prefix denoising for EXtreme compression) introduces a hierarchical latent space paired with asynchronous denoising over channel groups, enabling efficient extreme compression of images. The method orders channel prefixes from structure to detail, allowing a shared denoiser to generate them at staggered local times without adding tokens. On ImageNet-512, APEX outperforms existing methods at every evaluated channel count under 64x and 128x compression, and surpasses a 256-token model across all budgets when matched for training and guided sampling compute, especially at lower compute levels.
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...
The paper introduces SANA‑SR, an efficient one‑step diffusion restoration framework for real‑world image super‑resolution. It uses a deep compression autoencoder to reduce latent tokens by a 32× ratio, preserving essential structures and textures, and applies a linear‑attention DiT with LoRA fine‑tuning for linear‑complexity token mixing. Experiments show competitive or superior performance on benchmark datasets, and the pruned model runs in 0.019 s with 407.95 G MACs and 344 M parameters, indicating strong potential for mobile deployment.
arXiv:2610.10524v1 Announce Type: new Abstract: Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fe...
SpeeDiff is a latent diffusion model that jointly trains a VAE and diffusion network from scratch, using a Tweedie Pixel Reconstruction loss to prevent latent collapse. The approach allows scaling a transformer‑based architecture and improves representation alignment. Experiments show the SpeeDiff‑XL model trains 140× faster than Vanilla SiT and 61× faster than REPA, achieving an FID of 1.50 on ImageNet 256×256 and 1.53 on 512×512 without guidance.
arXiv:2610.09311v1 Announce Type: new Abstract: Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive...
The paper introduces VoRTeC, a video compression framework that leverages a foundational flow model to encode latent video representations compactly and predict their positions along flow trajectories. By integrating multi‑scale priors and avoiding access to flow‑matching network parameters, VoRTeC achieves one‑step decoding with high perceptual fidelity, while maintaining temporal consistency through tail‑frame reuse and prior caching. Experiments show a 58% reduction in bit consumption compared to prior diffusion‑based methods and a decoding speed increase ranging from 3 to 197 times, reaching 13 FPS at 720p and 32 FPS at 480p.
arXiv:2608.28730v1 Announce Type: cross Abstract: Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment....
arXiv:2602. 13357v3 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure.
arXiv:2607. 14898v1 Announce Type: cross Abstract: Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video.
arXiv:2609.03641v2 Announce Type: replace Abstract: Progressive image compression requires a single embedded representation whose received prefixes can be decoded without re-encoding the source. Mode...
The paper introduces a new training strategy for flow matching models that replaces co‑denoising pretrained representations, such as DINO, with direct prediction of those representations. By conditioning the model on its own prediction, the method eliminates the need for a second denoising trajectory and complex schedules, leading to faster convergence and higher generation quality. Experiments on ImageNet show state‑of‑the‑art performance in latent space with half the training epochs and a 20% FID improvement in pixel space compared to prior methods.
arXiv:2609.37080v1 Announce Type: new Abstract: Latent Diffusion Models (LDMs) typically adopt a two-stage pipeline: an auto-encoder (AE) is first pre-trained to define a latent space, then a diffusi...