影响力指数

-/100

发表论文2 篇

平均评分3.5

年均产出2.0 篇/年

Zhengwen Zeng

Researcher@Ant Group·中国·OpenReview

研究方向

Reinforcement Learning

Calibrated Self-Verification for Multimodal LLMs via Advantage-Decoupled Preference Optimization

ICLR 2026Withdrawn

Mitigating Conversational Inertia in Multi-Turn Agents through Context Bias Calibration

ICLR 2026Rejected

合作者 (9)