相关论文: AutoRefiner: Improving Autoregressive Video Diffus…

Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection…

Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods. However, these models struggle to maintain temporal consistency, as they are trained on static images,…

Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring…

We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing discrete diffusion (Austin et al., 2021), which we show are special…

Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous depth prediction. We…

Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained…

We introduce DiverseVAR, a framework that enhances the diversity of text-conditioned visual autoregressive models (VAR) at test time without requiring retraining, fine-tuning, or substantial computational overhead. While VAR models have…

The Reflow operation aims to straighten the inference trajectories of the rectified flow during training by constructing deterministic couplings between noises and images, thereby improving the quality of generated images in single-step or…

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inconsistencies and motion artifacts. To overcome this, we…

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale…

Real-image super-resolution (Real-ISR) seeks to recover HR images from LR inputs with mixed, unknown degradations. While diffusion models surpass GANs in perceptual quality, they under-reconstruct high-frequency (HF) details due to a…

Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…

Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on…

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the…

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally…