Shen Zhang

3

Papers

28

Total Citations

Papers (3)

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

NeurIPS 2025arXiv

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

NeurIPS 2025arXiv

Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance