News

2025

  • August 2025 Announcing DINOv3, a major release that raises the bar of self-supervised vision foundation models 🦖🦖🦖

  • July 2025 Publishing DINO-world, a latent video world model trained in the feature space of DINOv2. Also presented at ICML 2025 in Vancouver 🍁

  • June 2025 See you in Nashville, Tennessee, for CVPR 2025 🤠🪕

  • May 2025 Our work on scalable pre-training of dense image representations, CAPI, is accepted at TMLR. Congrats to Timothée for leading this work!

  • Feb 2025 Our “DINO.txt” paper on aligning vision and language representations is accepted at CVPR 2025.

2024

  • Oct 2024 Presenting my work on obtaining object-centric representations by clustering DINOv2 features at the FAIR conference in New York.

2023

  • Sept 2023 I’m moving to Paris to join the DINO team at Meta AI as a postdoctoral researcher 🦖

  • Jun 2023 PhD Graduation at KTH, Stockholm 🎓🎉

  • Feb 2023 Our work on semantic image compression with quantized autoencoders is accepted at ICASSP 2023 (Meta AI internship).

2022

2021

  • Sept 2021 Started a summer internship at Huawei Research in Dublin!

  • Jan 2021 My master student Jindong Wu graduated with a thesis on pooling strategies for Graph Networks.

2020 and older