影响力指数

59.57/100

前 4.9%

全站排名 #3,173

发表论文8 篇

平均评分5.6

年均产出2.7 篇/年

Bolian Li

PhD student@Purdue University·美国·OpenReview

研究方向

Efficient LLM Inference · LLM Post-Training · MC Sampling · Bayesian Deep Learning · Data Imbalance · Uncertainty Quantification

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

ICLR 2026Poster

Cascade Reward Sampling for Efficient Decoding-Time Alignment

COLM 2025Poster

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

COLM 2025Poster

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

ICLR 2025Poster

Cascade Reward Sampling for Efficient Decoding-Time Alignment

ICLR 2025Rejected

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization

ICML 2025Poster

Stochastic Steepest Descent with Acceleration for $\ell_p$-Smooth Non-Convex Optimization

ICLR 2025Rejected

合作者 (19)

博士导师8 篇