3 papers
cs.LG2026
AsyncOPD: How Stale Can On-Policy Distillation Be?
Wonjun Kang, Kevin Galim, Seunghyuk Oh +9
On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Li…
cs.LG2026
Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
Jungtaek Kim, Thomas Zeng, Ziqian Lin +5
Effective problem solving with Large Language Models (LLMs) can be enhanced when they are paired with external search algorithms. By viewing the space of diverse ideas and their fo…
cs.CV2025
OASIS: Online Sample Selection for Continual Visual Instruction Tuning
Minjae Lee, Minhyuk Seo, Tingyu Qu +2
In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data signific…