3 articles tagged with #sampling-methods. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose Embedded Runge-Kutta Guidance (ERK-Guid), a new method that improves diffusion model sampling by using solver-induced errors as guidance signals. The technique addresses stiffness issues in ODE trajectories and demonstrates superior performance over existing methods on ImageNet benchmarks.
Researchers introduce Kinetic Path Energy (KPE), a physics-inspired metric for evaluating flow-based generative models that measures the dynamical effort of sampling trajectories. The analysis reveals a non-monotonic relationship between trajectory energy and generation quality, where excessive energy causes memorization rather than genuine generation, leading to a training-free inference method called Kinetic Trajectory Shaping that improves output fidelity.
The article introduces GIST, a new development in smart sampling algorithms. This appears to be a theoretical advancement in algorithmic approaches to data sampling, though specific technical details and applications are not provided in the brief article body.
