Diffusing Differentiable Representations
–Neural Information Processing Systems
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method achieves sampling by "pulling back" the dynamics of the
Neural Information Processing Systems
Nov-17-2025, 19:41:55 GMT
- Country:
- North America > United States
- California (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- North America > United States
- Genre:
- Research Report > Experimental Study (0.93)
- Workflow (0.67)
- Industry:
- Information Technology (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence