Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/19ICML 2026Poster

Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at Scale

Jiajun Zhang · Yuheng Jing · Zeyu Cui · Hao Zheng · Wentao Chen · Kaixin LI · Jiaxi Yang · Tianbao Xie · Zeyao Ma · Tianyi Bai · KaShun SHUM · Lei Zhang · Kai Li · Jian Cheng · Zilei Wang · Qiang Liu · Liang Wang · Junyang Lin · Binyuan Hui

强化学习与后训练代码OpenReview

作者位次 #3/10ICML 2026Poster

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

Jiajun Zhang · Jianke Zhang · Zeyu Cui · Jiaxi Yang · Lei Zhang · Zilei Wang · Qiang Liu · Liang Wang · Binyuan Hui · Junyang Lin

多模态OpenReview

作者位次 #2/12ACL 2026Poster· Natural Language Processing

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

Jiajun Zhang · Zeyu Cui · Jiaxi Yang · Lei Zhang · Yuheng Jing · Zeyao Ma · Tianyi Bai · Zilei Wang · Qiang Liu · Liang Wang · Binyuan Hui · Junyang Lin

摘要

The dominant Fill-in-the-Middle (FIM) paradigm for code completion is constrained by its rigid inability to correct contextual errors and reliance on unaligned, insecure Base models. While Chat LLMs offer safety and Agentic workflows provide flexibility, they suffer from performance degradation a...

效率与系统对齐与偏好安全OpenReview 项目页

Zeyu Cui

获取完整研究档案

联系方式

2026 顶会论文

Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at Scale

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

常见合作者