Evidence for cross-modal representational convergence weakens substantially at scale and in realistic many-to-many settings, indicating models learn rich but distinct representations.
Cycle consistency as reward: Learning image- text alignment without human preferences
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
method 1
citation-polarity summary
fields
cs.CV 3years
2026 3representative citing papers
Reward models used as quality scorers in text-to-image generation encode demographic biases that cause reward-guided training to sexualize female subjects, reinforce stereotypes, and reduce diversity.
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
citing papers explorer
-
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.