Scholar
Andrei Bursuc
Google Scholar ID: HTfERCsAAAAJ
valeo.ai
Citations & Impact
Citations
3,314
H-index
26
i10-index
39
Publications
20
Co-authors
54
list available
Publications
Cited
1
Resume (English only)
Academic Achievements
- Jul 2025: Team released Franca, a fully open-sourced vision foundation model matching or outperforming DINOv2, SigLIPv2, and CLIP (ViT-G) on multiple benchmarks
- Jun 2025: Two papers (DIP and FLOSS) accepted to ICCV 2025
- Apr 2025: Serving as Area Chair for NeurIPS 2025
- Mar 2025: Organizing two workshops at CVPR 2025: 'Uncertainty Quantification for Computer Vision' and 'Embodied Intelligence for Autonomous Systems'
- Feb 2025: Released VaViM (1.2B-parameter video generative model) and VaVAM, achieving SOTA on NeuroNCAP driving benchmark
- Jan 2025: Paper 'MOCA' (published in TMLR) shortlisted for oral presentation at ICLR 2025
- Sep 2024: Paper 'No Train, all Gain' accepted to NeurIPS 2024
- Sep 2024: Serving as Area Chair for CVPR 2025
- Oct 2024: Published technical report 'The BRAVO Semantic Segmentation Challenge Results in UNCV2024'
- Jul 2024: Paper 'CLIP-DINOiser' accepted (conference name truncated)
Research Experience
- Current Research Scientist and Deputy Scientific Director at valeo.ai
- Research Associate at Inria Astra project team
- Former Research Scientist at Safran Tech
- Postdoctoral researcher at Inria Paris within the Willow project team, collaborating with Josef Sivic and Ivan Laptev on video crowd analysis
- Postdoc with Hervé Jégou at Inria Bretagne in 2014, working on kernelized visual descriptors for image retrieval and fine-grained classification in the FIRE-ID project
