4 papers
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Lijiang Li, Zuwei Long, Yunhang Shen +6
While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving…
VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing
Jiacheng Xu, Heting Gao, Liufei Xie +8
Human speech conveys expressiveness beyond linguistic content, including personality, mood, or performance elements, such as a comforting tone or humming a song, which we formalize…
Diffusion Sampling Correction via Approximately 10 Parameters
Guangyi Wang, Wei Peng, Lijiang Li +3
While powerful for generation, Diffusion Probabilistic Models (DPMs) face slow sampling challenges, for which various distillation-based methods have been proposed. However, they t…
PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores
Guangyi Wang, Yuren Cai, Lijiang Li +2
Diffusion Probabilistic Models (DPMs) have shown remarkable potential in image generation, but their sampling efficiency is hindered by the need for numerous denoising steps. Most…