A geometric view of semantic anisotropy in diffusion latents motivates a prompt-residual seed-shaping method that improves prompt alignment and visual quality without training.
arXiv preprint arXiv:2310.16656 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
GAVEL introduces a joint task, dataset, and benchmark for verifying, explaining, and localizing caption-image misalignments, with a supervised baseline that improves grounding and explanation metrics over strong closed-source models.
HRFD aligns multi-dimensional preferences in text-to-image diffusion via hierarchical relevance feedback and statistical distribution divergence measurement between liked and disliked image sets, remaining training-free and model-agnostic.
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
citing papers explorer
-
Determinism of Randomness: Prompt-Residual Seed Shaping for Diffusion Generation
A geometric view of semantic anisotropy in diffusion latents motivates a prompt-residual seed-shaping method that improves prompt alignment and visual quality without training.
-
GAVEL: Grounded Caption Error Verification and Localization
GAVEL introduces a joint task, dataset, and benchmark for verifying, explaining, and localizing caption-image misalignments, with a supervised baseline that improves grounding and explanation metrics over strong closed-source models.
-
Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion
HRFD aligns multi-dimensional preferences in text-to-image diffusion via hierarchical relevance feedback and statistical distribution divergence measurement between liked and disliked image sets, remaining training-free and model-agnostic.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.