Yusuke Kato

LaViDa: A Large Diffusion Language Model for Multimodal Understanding

arXiv 2025

Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

reflect-dit-inference-time-scaling-for-text

MobileWorldBench: Towards Semantic World Modeling For Mobile Agents

arXiv 2025

OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

CVPR 2025 1

Aligning Diffusion Models by Optimizing Human Utility

arXiv 2024

Hierarchical Open-vocabulary Universal Image Segmentation

hierarchical-open-vocabulary-universal-image

Refine and Represent: Region-to-Object Representation Learning

arXiv 2022

Kazuki Kozuka

Konstantinos Kallidromitis

Shufan Li

Akash Gokul

Aditya Grover

Trevor Darrell

professor

Arsh Koneru

Colorado J. Reed

Hritik Bansal

grad-student

Jason Kuen