Tianyi Lin
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
ML×2AI×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.
Efficient Exploration for Iterative Nash Preference Optimization
The paper proposes a novel, explicitly exploratory iterative Nash Learning from Human Feedback (NLHF) algorithm that achieves strong regret bounds for optimizing LLMs based on complex, non-scalar human preferences.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIRecentMay 31, 2026
Efficient Exploration for Iterative Nash Preference Optimization
The paper proposes a novel, explicitly exploratory iterative Nash Learning from Human Feedback (NLHF) algorithm that achieves strong regret bounds for optimizing LLMs based on complex, non-scalar huma…
View →
cs.LGcs.CLRecentMay 29, 2026