Related papers: Toward Diffusible High-Dimensional Latent Spaces: …

This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…

Image inpainting plays a vital role in restoring missing image regions and supporting high-level vision tasks, but traditional methods struggle with complex textures and large occlusions. Although Transformer-based approaches have…

Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing tokenizers are primarily designed to improve reconstruction fidelity or inherit pretrained…

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions…

Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by…

Multi-agent collaboration enhances the perception capabilities of individual agents through information sharing. However, in real-world applications, differences in sensors and models across heterogeneous agents inevitably lead to domain…

Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet such flexibility introduces a critical challenge: inference…

Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These…

Diffusion Models achieve state-of-the-art performance in generating new samples but lack a low-dimensional latent space that encodes the data into editable features. Inversion-based methods address this by reversing the denoising…

Decomposing complex data into factorized representations can reveal reusable components and enable synthesizing new samples via component recombination. We investigate this in the context of diffusion-based models that learn factorized…

Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

Reward Feedback Learning (ReFL) has recently shown great potential in aligning model outputs with human preferences across various generative tasks. In this work, we introduce a ReFL framework, named DiffusionReward, to the Blind Face…

Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware…

Recovering ghost-free High Dynamic Range (HDR) images from multiple Low Dynamic Range (LDR) images becomes challenging when the LDR images exhibit saturation and significant motion. Recent Diffusion Models (DMs) have been introduced in HDR…

The Transformer model has shown leading performance in time series forecasting. Nevertheless, in some complex scenarios, it tends to learn low-frequency features in the data and overlook high-frequency features, showing a frequency bias.…

Generating sewing patterns in garment design is receiving increasing attention due to its CG-friendly and flexible-editing nature. Previous sewing pattern generation methods have been able to produce exquisite clothing, but struggle to…

In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of…

Scientific measurements are often bottlenecked by suboptimal conditions, whether that be noise, incomplete spatial coverage, or limited resolution, rendering accurate field reconstruction a difficult task. We introduce LatentPDE, a latent…

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…