Hilde Kuehne
Scholar

Hilde Kuehne

Google Scholar ID: pxhCcH0AAAAJ
Tuebingen AI Center, University of Tuebingen, MIT-IBM Watson Lab
Multimodal learningVideo understandingAction RecognitionComputer visionMachine learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
7,264
 
H-index
31
 
i10-index
49
 
Publications
20
 
Co-authors
134
list available
Contact
No contact links provided.
Publications
18 items
TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning
2026
Cited
0
MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data
2026
Cited
0
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
2026
Cited
0
CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models
2026
Cited
0
When LLaVA Meets Objects: Token Composition for Vision-Language-Models
2026
Cited
0
AMoE: Agglomerative Mixture-of-Experts Vision Foundation Model
2025
Cited
0
Towards Audio Token Compression in Large Audio Language Models
2025
Cited
0
VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
2025
Cited
0
Resume (English only)
Co-authors
134 total
Rogerio Feris
Rogerio Feris
Research Manager, MIT-IBM Watson AI Lab
Thomas Serre
Thomas Serre
Professor, Brown University and ANR-3IA Artificial and Natural Intelligence Toulouse Institute
James Glass
James Glass
MIT Computer Science and Artificial Intelligence Laboratory
Juergen Gall
Juergen Gall
University of Bonn, Lamarr - Institute for Machine Learning and Artificial Intelligence
Leonid Karlinsky
Leonid Karlinsky
Principal Research Scientist, MIT-IBM Watson AI Lab, IBM Research
Nina Shvetsova
Nina Shvetsova
University of Tuebingen
Andrew Rouditchenko
Andrew Rouditchenko
PhD Student at MIT CSAIL
Anna Kukleva
Anna Kukleva
Max Planck Institute for Informatics