Julius Hense
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Vision×1
Frequent co-authors
Research Timeline
2026
In-Context Multiple Instance Learning
The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.
Highlighted terms show continued research focus across papers