paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

WQ

Wenwen Qiang

AAAI 2026×4CVPR 2026×2ICML 2026×2多模态强化学习与后训练安全对齐与偏好智能体与工具

新星分资深

45

一作贡献30

核心/参与20

方向广度16

合作网络12

1 一作 · 8 篇 · AAAI 2026 / CVPR 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

8

作者位次 #3/4ICML 2026Poster

Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning

Kunlun Xu · YanQin Zhang · Wenwen Qiang · Jiahuan Zhou

对齐与偏好多模态OpenReview

一作ICML 2026Poster· Deep Learning / Large Language Models

On the Plasticity and Stability for Post-Training Large Language Models

Wenwen Qiang · Ziyin Gu · Jiahuan Zhou · Jie Hu · Jingyao Wang · Changwen Zheng · Hui Xiong

强化学习与后训练OpenReview

作者位次 #3/6CVPR 2026Poster· Computer Vision & Pattern Recognition

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

Peizheng Guo · Jingyao Wang · Wenwen Qiang · Jiahuan Zhou · Changwen Zheng · Gang Hua

安全多模态强化学习与后训练OpenReview 项目页

作者位次 #5/9CVPR 2026Poster· Computer Vision & Pattern Recognition

SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMs

Ran Zuo · Haoxiang Hu · Chenxi Pei · Yanxuan Liu · Wenwen Qiang · Fang Liu · Xiaoming Deng · Cuixia Ma · Yong-jin Liu

多模态OpenReview 项目页

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration

Huijie Guo · Jingyao Wang · Peizheng Guo · Xingchen Shen · Changwen Zheng · Wenwen Qiang

作者位次 #4/6AAAI 2026Poster· Artificial Intelligence

TMAE: Learning Targeted Multi-Agent Exploration via Causal Inference

Chuxiong Sun · Dunqi Yao · Rui Wang · Wenwen Qiang · Changwen Zheng · Jiangmeng Li

智能体与工具效率与系统OpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

Group Causal Policy Optimization for Post-Training Large Language Models

Ziyin Gu · Jingyao Wang · Ran Zuo · Chuxiong Sun · Zeen Song · Changwen Zheng · Wenwen Qiang

强化学习与后训练OpenReview

作者位次 #4/4AAAI 2026Poster· Artificial Intelligence

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction

Ruike Song · Zeen Song · Huijie Guo · Wenwen Qiang

推理安全OpenReview

常见合作者

JWJingyao Wang×4 JZJiahuan Zhou×3 CZChangwen Zheng×3 ZGZiyin Gu×2 CZChangwen Zheng×2 PGPeizheng Guo×2 RZRan Zuo×2 HGHuijie Guo×2 CSChuxiong Sun×2 ZSZeen Song×2 KXKunlun Xu YZYanQin Zhang