Anna Rohrbach
Scholar

Anna Rohrbach

Google Scholar ID: GHpxNQIAAAAJ
Professor, TU Darmstadt, Germany
Vision and LanguageArtificial IntelligenceMultimodal Grounded Learning
Citations & Impact
All-time
Citations
9,382
 
H-index
37
 
i10-index
53
 
Publications
20
 
Co-authors
28
list available
Contact
No contact links provided.
Resume (English only)
Academic Achievements
  • 2025: 'Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection' accepted at NeurIPS 2025
  • 2025: 'Classifiers Understand Compositionality, but Conditions Apply' accepted at NeurIPS 2025 D&B
  • 2025: 'When To Solve, When To Verify...' accepted at COLM 2025
  • 2025: Multimodal fact-checking method DEFAME accepted at ICML 2025
  • 2024: Team won 1st place in AVERITEC Shared Task (FEVER Workshop @ EMNLP 2024)
  • 2023: Recipient of DAGM German Pattern Recognition Award
  • 2022: Team won Ego4D PNR Temporal Localization Challenge
  • Served as Area Chair for ICCV, CVPR, NeurIPS D&B across multiple years
  • Recognized as Outstanding Reviewer at CVPR and NeurIPS (2021–2022)
  • 2024: Honored as Outstanding Area Chair at ECCV
  • Lead of the 'Reasonable Artificial Intelligence (RAI)' project, funded as a Cluster of Excellence
Background
  • Research at the intersection of vision and language
  • Focus on building explainable and compositional models
  • Dedicated to diagnosing and mitigating bias in AI systems
  • Developing multimodal models that can learn from language advice
  • Work spans image/video captioning, visual grounding, visual question answering, text-to-image synthesis, and multimodal forensics