相关论文: ACDiT: Interpolating Autoregressive Conditional Mo…

We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…

Transformer-based autoregressive models excel in data generation but are inherently constrained by their reliance on discretized tokens, which limits their ability to represent continuous values with high precision. We analyze the…

Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critical limitation of…

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a…

The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge.…

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Analog circuit design consists of the pre-layout and layout phases. Among them, the pre-layout phase directly decides the final circuit performance, but heavily depends on experienced engineers to do manual design according to specific…

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…

While diffusion models excel at image synthesis, useful representations have been shown to emerge from generative pre-training, suggesting a path towards unified generative and discriminative learning. However, suboptimal semantic flow…

Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to…

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of…

Whole-body multi-modal human motion generation poses two primary challenges: creating an effective motion generation mechanism and integrating various modalities, such as text, speech, and music, into a cohesive framework. Unlike previous…

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straightforward modeling…