4 papers
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh +8
We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific l…
Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation
Gayatri Deshmukh, Somsubhra De, Chirag Sehgal +2
Specialized datasets that capture the fashion industry's rich language and styling elements can boost progress in AI-driven fashion design. We present FLORA, (Fashion Language Outf…
ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis
Onkar Susladkar, Gayatri Deshmukh, Yalcin Tur +2
Synthesizing medical images remains challenging due to limited annotated pathological data, modality domain gaps, and the complexity of representing diffuse pathologies such as liv…
D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods
Onkar Susladkar, Gayatri Deshmukh, Sparsh Mittal +1
In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style tran…