Jingyang Zhang

4

Papers

21

Total Citations

Papers (4)

Matrix3D: Large Photogrammetry Model All-in-One

Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training