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

Yongbo He

ACL 2026×2CVPR 2026多模态效率与系统对齐与偏好安全强化学习与后训练
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 / CVPR 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CVPR 2026Poster· Computer Vision & Pattern Recognition

Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation

Yongbo He · Zirun Guo · Tao Jin

作者位次 #3/8ACL 2026Poster· Natural Language Processing

SAME : Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation

Lujia Yang · Weicai Yan · Yongbo He · Qifei Zhang · Tao Jin · Jinshan Zhang · Meng Xi · Jianwei Yin

摘要

Sign language translation (SLT) is essential for bridging communication between the deaf and hearing communities, but real-world deployment suffers from domain shift such as signer variability, lighting, and background changes. Supervised fine-tuning is impractical due to limited labeled data, an...

效率与系统对齐与偏好多模态OpenReview 项目页
作者位次 #5/9ACL 2026Findings· Findings of ACL

Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and B ayesian Distillation

Boyun Zhang · Zequn Xie · Fangming Feng · Zihan Zhang · Yongbo He · Chuxin Wang · Sihang Cai · Tao Jin · Qifei Zhang

摘要

Multimodal Sentiment Analysis (MSA) models typically suffer significant performance degradation under domain shifts. While Test-Time Adaptation (TTA) aims to mitigate this, existing discriminative approaches often succumb to “confident but wrong” predictions on out-of-distribution samples. Conver...

安全多模态强化学习与后训练OpenReview 项目页

常见合作者