Arena-T2I Hard benchmark with ~30 decomposed constraints per prompt and a dependency-aware checklist reward yields better faithfulness-aesthetics trade-off than single-reward or weighted-sum baselines on SD3.5-Medium and FLUX.1-dev.
Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-image generation.arXiv preprint arXiv:2310.18235
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
EPIC introduces predicate-guided inference-time search that lifts compositional T2I prompt accuracy from 34% to 71% on GenEval2 with 31-81% lower execution costs.
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
citing papers explorer
-
Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist
Arena-T2I Hard benchmark with ~30 decomposed constraints per prompt and a dependency-aware checklist reward yields better faithfulness-aesthetics trade-off than single-reward or weighted-sum baselines on SD3.5-Medium and FLUX.1-dev.
-
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
EPIC introduces predicate-guided inference-time search that lifts compositional T2I prompt accuracy from 34% to 71% on GenEval2 with 31-81% lower execution costs.
-
ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.
-
CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.