Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh, Kiet Nguyen, Jiaxun Zhang, Adheesh Juvekar, Tianshu Bao, Lin Chai
Abstract
We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and representation entanglement, while a novel reference-based multimodal preference alignment optimizes relative outcomes under identical conditioning, improving faithfulness and controllability without large-scale retraining. UniDFlow achieves SOTA performance across eight benchmarks and exhibits strong zero-shot generalization to tasks including inpainting, in-context image generation, reference-based editing, and compositional generation, despite no explicit task-specific training.
BibTeX
@inproceedings{
susladkar2026best,
title={Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching},
author={Onkar Kishor Susladkar and Tushar Prakash and Gayatri Deshmukh and Kiet A. Nguyen and Jiaxun Zhang and Adheesh Sunil Juvekar and Tianshu Bao and Lin Chai and Sparsh Mittal and Inderjit S Dhillon and Ismini Lourentzou},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=hZhJTTjmUM}
}