3 papers
cs.CV2026
Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generation
Sanjana Reddy, Ishaan Malhi, Sally Ma +1
Existing methods for preference tuning of text-to-image (T2I) diffusion models often rely on computationally expensive generation steps to create positive and negative pairs of ima…
cs.CV2025
Preserving Product Fidelity in Large Scale Image Recontextualization with Diffusion Models
Ishaan Malhi, Praneet Dutta, Ellie Talius +5
We present a framework for high-fidelity product image recontextualization using text-to-image diffusion models and a novel data augmentation pipeline. This pipeline leverages imag…
cs.CL2021
Surfer100: Generating Surveys From Web Resources, Wikipedia-style
Irene Li, Alexander Fabbri, Rina Kawamura +7
Fast-developing fields such as Artificial Intelligence (AI) often outpace the efforts of encyclopedic sources such as Wikipedia, which either do not completely cover recently-intro…