Related papers: Skrr: Skip and Re-use Text Encoder Layers for Memo…
Discrete Diffusion Language Models have emerged as a compelling paradigm for unified multimodal generation, yet their deployment is hindered by high inference latency arising from iterative decoding. Existing acceleration strategies often…
Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. Starting from random noise, such text-to-image diffusion models gradually synthesize images in an iterative fashion…
Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to…
Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified prompts, leading to suboptimal image-text alignment, aesthetics, and quality. We propose a…
Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…
Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…
Realistic image restoration is a crucial task in computer vision, and diffusion-based models for image restoration have garnered significant attention due to their ability to produce realistic results. Restoration can be seen as a…
Transformer-based diffusion models offer superior scalability and performance but suffer from high computational overhead due to the iterative nature and quadratic complexity of self-attention at high resolutions. In this paper, we propose…
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those…
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…
Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a…
Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…
Most existing image restoration methods use neural networks to learn strong image-level priors from huge data to estimate the lost information. However, these works still struggle in cases when images have severe information deficits.…
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…
The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces…
Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively…
We present a transfer-learning generative downscaling framework to reconstruct fine resolution satellite images from coarse scale inputs. Our approach combines a lightweight U-Net transfer encoder with a diffusion-based generative model.…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach to improving the efficiency of Transformers by restricting self-attention…
The high computational costs of video super-resolution (VSR) models hinder their deployment on resource-limited devices, (e.g., smartphones and drones). Existing VSR models contain considerable redundant filters, which drag down the…