Ze Zhao

7

Papers

100

Total Citations

Papers (7)

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

NeurIPS 2025arXiv

EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning

NeurIPS 2025arXiv

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

NeurIPS 2025arXiv

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes