5 papers
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Yangming Shi, Shixiang Zhu, Tao Shen +14
We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the m…
High-Resolution Image Synthesis via Next-Token Prediction
Dengsheng Chen, Jie Hu, Tiezhu Yue +2
Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution…
Denoising with a Joint-Embedding Predictive Architecture
Dengsheng Chen, Jie Hu, Xiaoming Wei +1
Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains und…
Fine-gained Zero-shot Video Sampling
Dengsheng Chen, Jie Hu, Xiaoming Wei +1
Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necess…
Deformable 3D Shape Diffusion Model
Dengsheng Chen, Jie Hu, Xiaoming Wei +1
The Gaussian diffusion model, initially designed for image generation, has recently been adapted for 3D point cloud generation. However, these adaptations have not fully considered…