Shufan Li

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

From Masks to Worlds: A Hitchhiker's Guide to World Models

arXiv 2025

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

CVPR 2025 1

Aligning Diffusion Models by Optimizing Human Utility

arXiv 2024

xT: Nested Tokenization for Larger Context in Large Images

arXiv 2024

Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

arXiv 2024

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

arXiv 2024

Hierarchical Open-vocabulary Universal Image Segmentation

hierarchical-open-vocabulary-universal-image

InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following

arXiv 2023

Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

ICCV 2023 1

Refine and Represent: Region-to-Object Representation Learning

arXiv 2022

Aditya Grover

Kazuki Kozuka

Konstantinos Kallidromitis

Yusuke Kato

Akash Gokul

Trevor Darrell

professor

Colorado J. Reed

Harkanwar Singh

Hritik Bansal

grad-student

Ritwik Gupta