3 papers
cs.CV2025
MMaDA: Multimodal Large Diffusion Language Models
Ling Yang, Ye Tian, Bowen Li +4
We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal un…
cs.CL2025
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Yinjie Wang, Ling Yang, Bowen Li +3
We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, an…
cs.SD2025
Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement
Qianniu Chen, Xiaoyang Hao, Bowen Li +2
Zero-shot Text-To-Speech (TTS) synthesis shows great promise for personalized voice customization through voice cloning. However, current methods for achieving zero-shot TTS heavil…