Tianyang Hu

12

Papers

80

Total Citations

Papers (12)

Accelerating Diffusion Sampling with Optimized Time Steps

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning

Adding Additional Control to One-Step Diffusion with Joint Distribution Matching

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models