FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Training Deep Nets with Sublinear Memory Cost
- ESS-Flow: Training-free guidance as Bayesian inference in source space
- D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matching
- FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers
- Aligning Text-to-Image Diffusion Models with Reward Backpropagation
- Posterior sampling via Langevin dynamics based on generative priors
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs