影响力指数

49.43/100

前 8.9%

全站排名 #5,708

发表论文7 篇

平均评分6.3

年均产出2.3 篇/年

Zili Wang

Researcher@stepfun·中国·OpenReview

研究方向

Large language model

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling

ICLR 2026Rejected

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

ICLR 2026Poster

Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs

NeurIPS 2025Spotlight

Post-hoc Reward Calibration: A Case Study on Length Bias

ICLR 2025Poster

Layerwise Recurrent Router for Mixture-of-Experts

ICLR 2025Poster

合作者 (20)

Emmanouil Benetos