About

I'm a Research Scientist at Mistral AI, where I lead the Multimodal team.

Our team works across both pre-training and post-training, tackling a range of research questions, such as science of data, robotics and multimodal agents. If this sounds interesting to you — reach out!

Previously, I completed a PhD with the Visual Geometry Group (VGG) at the University of Oxford, working on representation learning in computer vision, where I was fortunate to be supervised by Andrew Zisserman and Andrea Vedaldi. During my PhD, I also spent time at Meta AI: first with Ishan Misra in New York, and then in the Segment Anything team with Ross Girshick.

Google Scholar

Selected Research

SAM 3 segmentation examples

SAM 3: Segment Anything with Concepts
SAM Team, Meta AI
ICLR 2026.
  Paper   Project Page   Code

Mistral 3 model family

Ministral 3
Mistral AI
Technical Report, 2026.
  Paper   Project Page

Magistral model artwork

Magistral
Mistral AI
Technical Report, 2025.
  Paper   Project Page

Pixtral 12B model artwork

Pixtral 12B
Mistral AI
Technical Report, 2024.
  Paper   Project Page

Category discovery representation comparison

No Representation Rules Them All in Category Discovery
Sagar Vaze, Andrea Vedaldi, Andrew Zisserman
NeurIPS 2023.
  Paper   Project Page   Code

Generalized Category Discovery overview

Generalized Category Discovery
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman
CVPR 2022.
  Paper   Project Page   Code

Open-set recognition results

Open-Set Recognition: A Good Closed-Set Classifier Is All You Need?
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman
ICLR 2022.
  Paper   Project Page   Code