Biao Gong

Ensuring Life-long Forgetting in Sequential Unlearning via Source-free Optimization

HieraQuery: Bridging Multimodal Understanding and High-Quality Generation through Multi-Scale Query Learning

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Framer: Interactive Frame Interpolation

VideoMAR: Autoregressive Video Generation with Continuous Tokens

LumiSculpt: A Consistency Lighting Control Network for Video Generation

UniVAE: A Unified Frame-Enriched Video VAE for Latent Video Diffusion Models