Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
arXiv preprint arXiv:2601.10129 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
Latent Action Control for Reasoning-Guided Unified Image Generation
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
- Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models