Related papers: DiTReducio: A Training-Free Acceleration for DiT-B…

We investigate the statistical and computational limits of latent Diffusion Transformers (DiTs) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs…

Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…

Diffusion Transformers require repeated denoiser evaluations during iterative sampling, making inference computationally expensive. Cache-based acceleration reduces this cost by reusing intermediate representations across denoising steps,…

Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary…

Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and…

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images…

Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans. More-recent Diffusion Transformers (DiTs) -- despite making significant headway in this context -- have only…

Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research value in areas such as immersive applications and artistic…

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

Diffusion models have recently advanced Combinatorial Optimization (CO) as a powerful backbone for neural solvers. However, their iterative sampling process requiring denoising across multiple noise levels incurs substantial overhead. We…

Diffusion models have achieved remarkable success in text-to-speech (TTS), even in zero-shot scenarios. Recent efforts aim to address the trade-off between inference speed and sound quality, often considered the primary drawback of…

In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS…

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves…

In this paper, we propose Tortoise and Hare Guidance (THG), a training-free strategy that accelerates diffusion sampling while maintaining high-fidelity generation. We demonstrate that the noise estimate and the additional guidance term…

Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the lengthy sampling time of the denoising process remains a significant bottleneck in…

While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public…

Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inference-time guidance methods such as classifier-free and…