Related papers: Hybrid Autoregressive-Diffusion Model for Real-Tim…

Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable parallel generation…

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned…

Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone…

Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical structures, existing…

Diffusion models achieve outstanding generative performance in various domains. Despite their great success, they lack semantic latent space which is essential for controlling the generative process. To address the problem, we propose…

The rapid evolution of the fashion industry increasingly intersects with technological advancements, particularly through the integration of generative AI. This study introduces a novel generative pipeline designed to transform the fashion…

For autoregressive modeling of chaotic dynamical systems over long time horizons, the stability of both training and inference is a major challenge in building scientific foundation models. We present a hybrid technique in which an…

Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution text-to-image generation remains largely unexplored. In…

LLMs have become the mainstream approaches to code generation. Existing LLMs mainly employ autoregressive generation, i.e. generating code token-by-token from left to right. However, the underlying autoregressive generation has two…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through…

Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies…

Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value (KV) caches. Block diffusion mitigates these issues, yet still enforces a fixed block size and…

Audio-driven talking head generation is a significant and challenging task applicable to various fields such as virtual avatars, film production, and online conferences. However, the existing GAN-based models emphasize generating…

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…

World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions…

Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…

Machine learning methods, such as diffusion models, are widely explored as a promising way to accelerate high-fidelity fluid dynamics computation via a super-resolution process from faster-to-compute low-fidelity input. However, existing…

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…