• 09/2025:   [New] Released AToken, a unified tokenizer for vision.

• 09/2025:   [New] Two papers accepted to NeurIPS 2025!

• 08/2025:   [New] Serve as Area Chair for CVPR 2026.

• 07/2025:   Released Apple Foundation Models [Tech report].

• 07/2025:   One paper accepted to COLM 2025!

• 01/2025:   Serve as Area Chair for AAAI 2026.

We're hiring Applied Scientists in Multimodal LLM and GenAI, both full-time and interns!

Hi, I am Mingze. I am a Senior Applied Scientist at Adobe Firefly. Before joining Adobe, I worked or interned at Apple, Cruise, Amazon, and Microsoft Research. My research interests lie primarily in the area of computer vision and machine learning, and my current focus is on developing unified encoders and LLMs for multi-modalities (text, image, video, and 3D) across understanding and generative tasks.

I received my Ph.D. degree in Computer Science from Indiana University in 2020, advised by Prof. David Crandall. I was a visiting student researcher at Georgia Institute of Technology in 2018, working with Prof. Dhruv Batra and Prof. Devi Parikh. I have served or am serving as an Area Chair for CVPR (2024–2026), AAAI (2026), and WACV (2023–2024).

(*Equal Contribution, ^†Corresponding Author)

• AToken: A Unified Tokenizer for Vision
  Jiasen Lu*, Liangchen Song*, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang
  Technical Report, 2025 [PDF]

• UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
  Rui Tian*, Mingfei Gao*, Mingze Xu*, Jiaming Hu, Jiasen Lu, Zuxuan Wu, Yinfei Yang, Afshin Dehghan
  Conference on Neural Information Processing Systems (NeurIPS), 2025 [PDF]

• StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
  Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, Ping Huang
  Conference on Neural Information Processing Systems (NeurIPS), 2025 [PDF]

• SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
  Mingze Xu*, Mingfei Gao*, Shiyu Li*, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan
  Conference on Language Modeling (COLM), 2025 [PDF]

• MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
  Apple MM1.5 Team
  International Conference on Learning Representations (ICLR), 2025 [PDF]

• SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
  Mingze Xu*, Mingfei Gao*, Zhe Gan, Hong-You Chen, Zhengfeng Lai, Haiming Gang, Kai Kang, Afshin Dehghan
  Technical Report, 2024 [PDF] [Code]

• SkeleTR: Towards Skeleton-based Action Recognition in the Wild
  Haodong Duan, Mingze Xu, Bing Shuai, Davide Modolo, Zhuowen Tu, Joseph Tighe, Alessandro Bergamo
  IEEE International Conference on Computer Vision (ICCV), 2023 [PDF]

• An In-depth Study of Stochastic Backpropagation
  Jun Fang, Mingze Xu^†, Hao Chen, Bing Shuai, Zhuowen Tu, Joseph Tighe
  Conference on Neural Information Processing Systems (NeurIPS), 2022 [PDF] [Code]

• MeMOT: Multi-Object Tracking with Memory
  Jiarui Cai, Mingze Xu^†, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral) [PDF]

• Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
  Feng Cheng, Mingze Xu^†, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Li, Wei Xia
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral) [PDF] [Code]

• TubeR: Tubelet Transformer for Video Action Detection
  Jiaojiao Zhao*, Yanyi Zhang*, Xinyu Li*, Hao Chen, Shuai Bing, Mingze Xu, Chunhui Liu, Kaustav Kundu, Yuanjun Xiong, Davide Modolo, Ivan Marsic, Cees Snoek, Joseph Tighe
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral) [PDF] [Code]

• DoTA: Unsupervised Detection of Traffic Anomaly in Driving Videos
  Yu Yao, Xizi Wang, Mingze Xu, Zelin Pu, Yuchen Wang, Ella Atkins, David Crandall
  IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022 [PDF] [Data]

• Stepwise Goal-Driven Networks for Trajectory Prediction
  Chuhua Wang*, Yuchen Wang*, Mingze Xu, David Crandall
  IEEE Robotics and Automation Letters (RA-L), 2022 [PDF] [Code]

• Long Short-Term Transformer for Online Action Detection
  Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Xia, Zhuowen Tu, Stefano Soatto
  Conference on Neural Information Processing Systems (NeurIPS), 2021 (Spotlight) [PDF] [Project page]

• Learning Self-Consistency for Deepfake Detection
  Tianchen Zhao, Xiang Xu, Mingze Xu, Hui Ding, Yuanjun Xiong, Wei Xia
  IEEE International Conference on Computer Vision (ICCV), 2021 (Oral) [PDF]

• Temporal Recurrent Networks for Online Action Detection
  Mingze Xu*, Mingfei Gao*, Yi-Ting Chen, Larry Davis, David Crandall
  IEEE International Conference on Computer Vision (ICCV), 2019 [PDF] [Code]

• StartNet: Online Detection of Action Start in Untrimmed Videos
  Mingfei Gao, Mingze Xu, Larry Davis, Richard Socher, Caiming Xiong
  IEEE International Conference on Computer Vision (ICCV), 2019 [PDF]

• Embodied Amodal Recognition: Learning to Move to Perceive Objects
  Jianwei Yang*, Zhile Ren*, Mingze Xu, Xinlei Chen, David Crandall, Devi Parikh, Dhruv Batra
  IEEE International Conference on Computer Vision (ICCV), 2019 [PDF]

• Unsupervised Traffic Accident Detection in First-Person Videos
  Mingze Xu*, Yu Yao*, Yuchen Wang, David Crandall, Ella Atkins
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019 [PDF] [Code]

• Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems
  Yu Yao, Mingze Xu, Chiho Choi, David Crandall, Ella Atkins, Behzad Dariush
  IEEE International Conference on Robotics and Automation (ICRA), 2019 [PDF] [Code]

• Joint Person Segmentation and Identification in Synchronized First- and Third-Person Videos
  Mingze Xu, Chenyou Fan, Yuchen Wang, Michael Ryoo, David Crandall
  European Conference on Computer Vision (ECCV), 2018 [PDF] [Project page]