A new adjoint matching framework formulates flow model alignment as optimal control, enabling direct regression training and terminal-trajectory truncation for efficiency gains on models like SiT-XL and FLUX.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Encoding user interactions into visual in-context example pairs turns static models into controllable systems that improve IoU, PSNR, and LPIPS on guided tasks without retraining.
citing papers explorer
-
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
A new adjoint matching framework formulates flow model alignment as optimal control, enabling direct regression training and terminal-trajectory truncation for efficiency gains on models like SiT-XL and FLUX.
-
From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks
Encoding user interactions into visual in-context example pairs turns static models into controllable systems that improve IoU, PSNR, and LPIPS on guided tasks without retraining.