Shuo Yang
- CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
- Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
- Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
- UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
- WorldModelBench: Judging Video Generation Models As World Models