analiza aiqbench
This research introduces TARA, a novel framework that improves text-to-image generation by intelligently allocating specific semantic repairs to address distinct prompt failures without retraining models. By separating diagnosis from compilation and enforcing single-prescription constraints, the method achieves superior accuracy while reducing inference time compared to existing optimizers like VisualPrompter. The approach advances machine learning techniques for refining generative AI outputs through structured error correction rather than uniform expansion.
One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization
arXiv:2607.18724v1 Announce Type: new Abstract: Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform prompt expansion, even though each calls for different repair language. We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt. We instantiate this formulation in the training-free Type-Aware Repair Allocation (TARA) framework, which separates diagnosis, allocation, compilation, and a semantic repair gate, an accept-or-revert controller over exactly one prescribed repair that prevents semantic regressions. Extensive experiments on DSG and TIFA across four frozen generators demonstrate that TARA achieves the best semantic accuracy in all eight benchmark-generator cells, improving over VisualPrompter by 5.6 and 2.6 points on DSG and TIFA, respectively, while maintaining image quality and running fastest in our matched local setting at 16.0 seconds versus 20.0 seconds per prompt.
Title:One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization
Abstract:Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform prompt expansion, even though each calls for different repair language. We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt. We instantiate this formulation in the training-free Type-Aware Repair Allocation (TARA) framework, which separates diagnosis, allocation, compilation, and a semantic repair gate, an accept-or-revert controller over exactly one prescribed repair that prevents semantic regressions. Extensive experiments on DSG and TIFA across four frozen generators demonstrate that TARA achieves the best semantic accuracy in all eight benchmark-generator cells, improving over VisualPrompter by 5.6 and 2.6 points on DSG and TIFA, respectively, while maintaining image quality and running fastest in our matched local setting at 16.0 seconds versus 20.0 seconds per prompt.
Artificial Intelligence (cs.AI)
arXiv:2607.18724 [cs.AI]
(or arXiv:2607.18724v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.18724 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 285 cuvinte
Subiecte conexe
A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises
KDnuggets · 10 sept. 2026
Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining
arXiv · 3 aug. 2026
Honest Abacus AI Review: ChatLLM, DeepAgent, AI Studio & More
KDnuggets · 4 aug. 2026
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
Latent Space · 12 sept. 2026