paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
ZC

Zhirui Chen

ACL 2026×2ICML 2026多模态检索与知识理论与学习动力学推理强化学习与后训练
新星分新星
84
一作贡献70
核心/参与12
方向广度13
合作网络6
2 一作 · 3 篇 · ACL 2026 / ICML 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
一作ICML 2026Poster· Applications / Computer Vision

Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning

Zhirui Chen · Ziwei Chen · Ling Shao

多模态检索与知识理论与学习动力学OpenReview
作者位次 #2/7ACL 2026Poster· Natural Language Processing

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories

Peiyang Liu · Zhirui Chen · Xi Wang · Di Liang · Youru Li · Zhi Cai · Wei Ye

摘要

Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches retain only the single highest-reward trajectory, discarding the comparative signals present in the many explored paths....

推理多模态强化学习与后训练OpenReview 项目页
一作ACL 2026Findings· Findings of ACL

S truct KV : Preserving the Structural Skeleton for Scalable Long-Context Inference

Zhirui Chen · Peiyang Liu · Ling Shao

摘要

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context inference. Existing compression approaches typically prior...

效率与系统检索与知识评测与基准OpenReview 项目页

常见合作者