Yao Shu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1NLP×1
Frequent co-authors
Research Timeline
2026
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the performance of expensive online reinforcement learning.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CLRecentMay 29, 2026
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
Jian Mu, Tianyi Lin, Chengwei Qin, Zhongxiang Dai +1 more
DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the p…
View →