Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Steer Away From Mode Collisions: Improving Composition In Diffusion Models
Debottam Dutta, Jianchong Chen, Rajalaxmi Rajagopalan +2
We propose to improve multi-concept prompt fidelity in text-to-image diffusion models. We begin with common failure cases - prompts like "a cat and a dog" that sometimes yields ima…
cs.CV2026
Personalized Image Generation via Human-in-the-loop Bayesian Optimization
Rajalaxmi Rajagopalan, Debottam Dutta, Yu-Lin Wei +1
Imagine Alice has a specific image in her mind, say, the view of the street in which she grew up during her childhood. To generate that exact image, she guides a generativ…