Ling Yang

Latest

• MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
• Mmada: Multimodal large diffusion language models
• Training-free heterogeneous graph condensation via data selection
• Towards scalable and deep graph neural networks via noise masking
• Training-free diffusion acceleration with bottleneck sampling
• Diffusion-sharpening: Fine-tuning diffusion models with denoising trajectory sharpening
• Hgamlp: Heterogeneous graph attention mlp with de-redundancy mechanism