🧑‍🔬 Sangjun Song

🏛️ Affiliations

🎓Seoul National UniversitySeoul · South Korea2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. KL for a KL: On-Policy Distillation with Control Variate Baseline (2026 · 8 citations)
   On-Policy Distillation (OPD) trains a student LLM on its own sampled outputs and pulls it toward a teacher by minimizing reverse KL.
2. ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding (2026 · 1 citation)
   Large Reasoning Models (LRMs) often overthink. They find a correct intermediate answer in their chain of thought, keep deliberating, and then replace it with a wrong one. The authors first measure this with Qwen3-4B-Thinking. They force the </think> delimiter at each sentence boundary and pick the best cut-off in…

🤝 Co-authors here

2 co-authors with a page, the most papers together first.

• Minjae Oh ×2
• Yohan Jo ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 9 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 3 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/sangjun-song/