inverse problems
Inverse problems in AI involve deducing the causes or parameters of a system from observed effects or outcomes, often requiring specialized methods due to their inherent challenges.
- Adversarial generalization of unfolding (model-based) networks
- Approximation theory for 1-Lipschitz ResNets
- Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
- Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions
- InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
- MAP Estimation with Denoisers: Convergence Rates and Guarantees
- Self-diffusion for Solving Inverse Problems
- Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes
- Split Gibbs Discrete Diffusion Posterior Sampling
- System-Embedded Diffusion Bridge Models
- Time-Embedded Algorithm Unrolling for Computational MRI