ControlLight introduces a controllable low-light enhancement model trained on a new large-scale real-world dataset using a misalignment-aware weighted flow matching loss for structural consistency across enhancement levels.
Slideredit: Continuous image editing with fine-grained instruction control.arXiv preprint arXiv:2511.09715, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Token-to-Token alignment rephrases prompts into shared structure then matches token embeddings by semantic similarity, making linear interpolation a meaningful operation for blending in text-to-image models.
citing papers explorer
-
ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement
ControlLight introduces a controllable low-light enhancement model trained on a new large-scale real-world dataset using a misalignment-aware weighted flow matching loss for structural consistency across enhancement levels.
-
Token-to-Token Alignment of Text Embeddings for Semantic Blending
Token-to-Token alignment rephrases prompts into shared structure then matches token embeddings by semantic similarity, making linear interpolation a meaningful operation for blending in text-to-image models.