影响力指数

-/100

发表论文3 篇

平均评分4.0

年均产出3.0 篇/年

Cong Ma

Researcher@ByteDance Inc.·中国·OpenReview

研究方向

Large Language Model · Reinforcement Learning with Human Feedback · Natural Language Processing

EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance

ICLR 2026Rejected

ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

ICLR 2026Rejected

ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?

ICLR 2026Desk Rejected

合作者 (10)