Jiaxi Gu

3

Papers

0

Total Citations

Papers (3)

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark