Sparse Context achieves 2-4x faster inference in reference-conditioned diffusion models by fine-tuning with random token dropping and applying task-aware selection at inference time, without loss of visual quality.
URL https://onlinelibrary
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping
Sparse Context achieves 2-4x faster inference in reference-conditioned diffusion models by fine-tuning with random token dropping and applying task-aware selection at inference time, without loss of visual quality.