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

Yanshu Li

ACL 2026×2ECCV 2026多模态对齐与偏好效率与系统强化学习与后训练智能体与工具
新星分新星
66
一作贡献30
核心/参与10
方向广度13
合作网络6
1 一作 · 3 篇 · ACL 2026 / ECCV 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
作者位次 #6/10ACL 2026Poster· Natural Language Processing

Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation

Xi Xiao · Chenrui Ma · Yunbei Zhang · Chen Liu · Zhuxuanzi Wang · Yanshu Li · Lin Zhao · Guosheng Hu · Tianyang Wang · Hao Xu

摘要

Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: \textit{semantic drift} , arising from treating all update directions with equal importance, and \textit{structural incoherence} , due to ad...

效率与系统多模态强化学习与后训练OpenReview 项目页
作者位次 #3/4ACL 2026Poster· Natural Language Processing

MM - S tance D et: Retrieval-Augmented Multi-modal Multi-agent Stance Detection

Weihai Lu · Zhejun Zhao · Yanshu Li · Huan He

摘要

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pa...

多模态智能体与工具推理OpenReview 项目页

常见合作者