1. Paper 'No Representation Rules Them All in Category Discovery', NeurIPS 2023.
2. Paper 'GeneCIS: A Benchmark for General Conditional Image Similarity', CVPR 2023 (Highlighted Paper, 2.5% of submissions).
3. Paper 'Zero-Shot Category-Level Object Pose Estimation', ECCV 2022.
4. Paper 'Generalized Category Discovery', CVPR 2022.
5. Paper 'Open-Set Recognition: a Good Closed-Set Classifier is All You Need?', ICLR 2022 (Oral, 1.6% of submissions).
6. Paper 'Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement', ICRA 2022.
7. Paper 'Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment', IEEE JBHI, 2020 (Impact Factor: ~4.2).
8. Paper 'Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks', AI For Social Good Workshop (Harvard CRCS).
9. Paper 'SMArtCast: Predicting soil moisture interpolations into the future using Earth observation data in a deep learning framework', Climate Change AI Workshop (ICLR 2020).
10. Paper 'Segmentation of Fetal Adipose Tissue Using Efficient CNNs for Portable Ultrasound', PIPPI Workshop (MICCAI 2018).
Research Experience
1. Research Scientist at Mistral AI, working on multi-modal language models.
2. Internship experiences at Meta AI (FAIR): worked with Ishan Misra in New York, and then joined the Segment Anything team with Ross Girshick.
Education
PhD from the VGG, Oxford University, supervised by Andrew Zisserman and Andrea Vedaldi
Background
Research Scientist, focusing on multi-modal language models. Completed a PhD at the VGG, Oxford University, working on representation learning in computer vision.