Original Works

Publications

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

  Colorado Reed*, Shufan Li*, Ritwik Gupta*, Sarah Brockman, Christopher Funk, Brian Clipp, Kurt Keutzer, Salvatore Candido, Matt Uyttendaele, Trevor Darrell

  [Arxiv]. ICCV 2023. (Oral)

  Scale-Aware representation learning with prior information of image scale.
• Hierarchical Open-vocabulary Universal Image Segmentation.

  Xudong Wang*, Shufan Li*, Konstantinos Kallidromitis*, Yusuke Kato, Kazuki Kozuka, Trevor Darrell

  [Arxiv]. NeurIPS 2023.

  Segmentating arbritrary objects and object parts using text prompts
• xT: Nested Tokenization for Larger Context in Large Images .

  Ritwik Gupta*, Shufan Li*, Tyler Zhu*, Jitendra Malik, Trevor Darrell, Karttikeya Mangalam

  [Arxiv]. ICML 2024.

  Long context visual perception on large images.
• Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data.

  Shufan Li*, Harkanwar Singh, Aditya Grover

  [Arxiv]. ECCV 2024 (Oral)

  Modeling multi-dimensional data with linear complexity.
• Aligning Diffusion Models by Optimizing Human Utility.

  Shufan Li*, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozukar

  [Arxiv] NeurIPS 2024

  Aligning text-to-image models with human feedback.
• SegLLM: Multi-round Reasoning Segmentation

  XuDong Wang*, Shaolun Zhang*, Shufan Li*, Konstantinos Kallidromitis, Kehan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell

  [Arxiv]. ICLR 2025.

  Multi-round interactive Segmention using Large Language Model
• InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following.

  Shufan Li*, Harkanwar Singh, Aditya Grover

  [Arxiv]. [Project Page] NAACL Findings 2025

  Image editing following multi-modal instructions.
• OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

  Shufan Li*, Konstantinos Kallidromitis*, Akash Gokul*, Zichun Liao, Yusuke Kato, Kazuki Kozuka, Aditya Grover

  [Arxiv]. CVPR 2025

  Universal Multimodal Diffusion Generative Model for Image, Audio and Text

Preprints

• LaViDa: A Large Diffusion Model for Vision-Language Understanding

  Shufan Li, Konstantinos Kallidromitis, Hritik Bansal, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Jason Kuen, Zhe Lin, Kai-Wei Chang, Aditya Grover

  [Website]. [Arxiv] 2025

  Universal Multimodal Diffusion Language Model for Vision-Language Understanding
• Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

  Shufan Li*, Konstantinos Kallidromitis*, Akash Gokul*, Arsh Koneru, Yusuke Kato, Kazuki Kozuka, Aditya Grover

  [Arxiv]. 2025

  In-Context Reflection Improves Text-to-Image Generation
• PopAlign: Population-Level Alignment for Fair Text-to-Image Generation

  Shufan Li*, Harkanwar Singh, Aditya Grover

  [preprint]. 2024.

  Aligning Diffusion Model For Fairness
• Refine and Represent: Region-to-Object Representation Learning

  Akash Gokul*, Konstantinos Kallidromitis*, Shufan Li*, Yusuke Kato, Kazuki Kozuka, Trevor Darrell, Colorado J Reed

  [preprint]. 2022.

  Representation learning benefits by first learning from image regions and then learning from actual objects.

Technical Reports

• Mercury: Ultra-Fast Language Models Based on Diffusion

  Samar Khanna*, Siddhant Kharbanda*, Shufan Li*, Harshit Varma*, Eric Wang* Sawyer Birnbaum , Ziyang Luo , Yanis Miraoui , Akash Palrecha Stefano Ermon , Aditya Grover , Volodymyr Kuleshov

  [website]. 2025.

  Frontier Diffusion Language Models (with Inception Labs)
• Interpreting Audiograms with Multi-stage Neural Networks

  Shufan Li*, Congxi Lu, Linkai Li,Jirong Duan, Xinping Fu, Haoshuai Zhou

  [Arxiv]. 2021.

  Accelerate Hearing Aid Fitting using Computer Vision (with Orka Labs)
• Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images

  Shufan Li*, Congxi Lu, Linkai Li, Haoshuai Zhou

  [preprint]. 2022.

  Line Chart Data Extraction in the wild.