Elias Ramzi
Scholar

Elias Ramzi

Google Scholar ID: mbfTD_UAAAAJ
Reasearch scientist, valeo.ai
Deep learningComputer Vision
Citations & Impact
All-time
Citations
130
 
H-index
6
 
i10-index
4
 
Publications
11
 
Co-authors
5
list available
Resume (English only)
Academic Achievements
  • Publications:
  • - Robust and Decomposable Average Precision for Image Retrieval (NeurIPS 2021)
  • - Hierarchical Average Precision Training for Pertinent Image Retrieval (ECCV 2022)
  • - Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection (ICML 2023)
  • - GalLoP: Learning Global and Local Prompts for Vision-Language Models (ECCV 2024)
  • - Optimization of Rank Losses for Image Retrieval (TPAMI 2025)
  • - VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (ArXiv Preprint 2025)
  • - LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension (ICLR 2025)
Research Experience
  • Working as a Research Scientist at valeo.ai; involved in multiple projects such as VaViM & VaVAM, LLM-wrapper, etc.
Education
  • PhD in Computer Vision from Cnam, supervised by Nicolas Thome (Sorbonne Université), Nicolas Audebert (IGN), and Clément Rambour (Cnam).
Background
  • Research Interests: Deep learning and computer vision. Professional Field: AI Research Scientist.
Miscellany
  • Personal interests not mentioned