Scholar
David T. Hoffmann
Google Scholar ID: yNMolb8AAAAJ
University of Freiburg
Transformers
Self-supervised Learning
Representation Learning
Synthetic Data
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
494
H-index
6
i10-index
6
Publications
12
Co-authors
0
Publications
5 items
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
2026
Cited
0
No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
2026
Cited
0
CLIP Won't Learn Object-Attribute Binding from Natural Data and Here is Why
2025
Cited
0
Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation
2025
Cited
0
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
2024
Cited
0
