Gradient-free Decoder Inversion in Latent Diffusion Models
–Neural Information Processing Systems
For example, recent video LDMs can generate more than 16 frames, but GPUs with 24 GB memory can only perform gradient-based decoder inversion for 4 frames.
Neural Information Processing Systems
Feb-16-2026, 19:41:45 GMT
- Country:
- Asia > South Korea
- Europe
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Italy > Calabria
- North America > United States
- California > Los Angeles County > Los Angeles (0.14)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Information Technology > Security & Privacy (0.46)
- Technology: