Ido Hakimi
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7Reinforcement Learning via Self-Distillation
arXiv 2026
ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
arXiv 2026
MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
arXiv 2025
From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
arXiv 2025
Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
arXiv 2025
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
arXiv 2025
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers