Dan Zhang

7

Papers

77

Total Citations

Papers (7)

ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation

Directly Denoising Diffusion Models