arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. M...
arXiv:2605. 18324v2 Announce Type: replace-cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.
arXiv:2608. 01298v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks.
arXiv:2606.21030v2 Announce Type: replace-cross Abstract: Diffusion-based image compression has achieved strong perceptual quality at ultra-low bitrates. However, existing codecs are often tied to sp...
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
arXiv:2607.01630v2 Announce Type: replace Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEr...
arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.
V-Co investigates visual co-denoising for pixel-space diffusion models, using a unified JiT-based framework to isolate key design choices. The study identifies two essential components: a dual-stream architecture with flexible cross-stream interaction and a perceptual-drifting hybrid loss combined with RMS-based feature rescaling for stronger semantic supervision. Experiments on ImageNet-256 demonstrate that V-Co surpasses baseline pixel-space diffusion and strong prior pixel-diffusion methods at comparable model sizes while requiring fewer training epochs.
The paper introduces the Superposed Latent Autoencoder (SLAE), a method that stores multiple wide latent representations together by superposing them into a single memory tensor using learned codes and randomized keys. SLAE eliminates the need for tight dimensional bottlenecks, achieving up to 56% lower reconstruction error on datasets such as CIFAR-10/100 and SVHN while maintaining the same storage budget. The approach also boosts downstream classification performance by up to 16.79 percentage points, demonstrating that wide representations can be effectively compressed through structured interference rather than dimensional reduction.
HP-UniIF is a unified vision framework that uses diffusion priors and a depth‑wise hierarchical conditional modulation strategy to support heterogeneous image fusion, visual restoration, and downstream perception tasks. The framework introduces task prompt modulation at bottleneck layers, a degradation prompt router at shallow layers, and an application prompt bank at decoding stages to decouple and adapt to different objectives. Experiments across multiple fusion tasks, degradations, and downstream applications show that HP‑UniIF achieves superior performance while maintaining visually faithful results and task‑relevant semantics.