Search Results for author:
Found 2 papers, 1 papers with code
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
This issue stems from the internal biases in text encoding, which overlooks motions, and inadequate conditioning mechanisms in T2V generation models.
MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency
However, existing DAS methods fail to trade off between model performance and model size.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
