DivRL introduces negative self-similarity measure and visual semantic matching with an explore-and-suppress gated strategy to jointly improve structural diversity and identity consistency in subject-driven generation.
arXiv preprint arXiv:2512.04784 (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
Introduces ProductConsistency dataset, benchmark, and Cyclic Consistency reward to fine-tune image editing models, achieving a 5x reduction in character error rate for product identity preservation.
citing papers explorer
-
DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation
DivRL introduces negative self-similarity measure and visual semantic matching with an explore-and-suppress gated strategy to jointly improve structural diversity and identity consistency in subject-driven generation.
-
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
Introduces ProductConsistency dataset, benchmark, and Cyclic Consistency reward to fine-tune image editing models, achieving a 5x reduction in character error rate for product identity preservation.