Scholar
Jonas Hübotter
Google Scholar ID: pxi_RkwAAAAJ
PhD student, ETH Zurich
artificial intelligence
machine learning
reinforcement learning
test time training
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
121
H-index
6
i10-index
5
Publications
14
Co-authors
22
list available
Publications
10 items
Task Vector Descent: Learning from Non-IID Batches
2026
Cited
0
Deep Epistemic Value Functions for Optimistic Exploration
2026
Cited
0
On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
2026
Cited
0
Majority Voting for Code Generation
2026
Cited
0
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
2026
Cited
0
Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
2025
Cited
0
Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
2025
Cited
0
Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
2025
Cited
0
Load more
Co-authors
14 total
Andreas Krause
Professor of Computer Science, ETH Zurich
Bhavya Sukhija
Doctoral Student, ETH Zürich
Lenart Treven
ETH Zürich
Ido Hakimi
Google Research
Yarden As
ETH Zürich
Georg Martius
University of Tübingen and Max Planck Institute for Intelligent Systems
Prof. Dr. Stelian Coros
ETH Zurich
Dongho Kang
Research scientist at RAI institute.
