FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
FlowAWR: 通过优势加权修正的在线自适应流强化
Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu
机构
*
Beihang University(北京航空航天大学)
;
Joy Future Academy(京东探索研究院)
;
Zhongguancun Academy(中关村学院)
;
Zhejiang University(浙江大学)
;
University of Science and Technology of China(中国科学技术大学)
On the Vulnerability of Parameter-Level Defenses to Model Merging
参数级防御对模型合并的脆弱性
Kuangpu Guo, Qingyan Zheng, Jian Liang, Yongcan Yu, Zilei Wang, Ran He, Tieniu Tan
机构
*
University of Science and Technology of China(中国科学技术大学)
;
NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences(自动化研究所国家工程实验室及机器智能研究所)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Xuan Zhao, Haonan He, Qingyu Yang, Minglei Li, Jingqi Ye, Zelin Tan, Bo Wan, Peng Ye
机构
*
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
;
University of Science and Technology of China(中国科学技术大学)
;
KTH Royal Institute of Technology(皇家理工学院)
;
Fudan University(复旦大学)
;
The Chinese University of Hong Kong(香港中文大学)
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
SrDetection: 一种用于代码大型语言模型中数据泄露检测的自参考框架
Shuaimin Li, Liyang Fan, Zeyang Li, Zhuoyue Wan, Yufang Lin, Shiwen Ni, Feiteng Fang, Hamid Alinejad-Rokny, Yuanfeng Song, Kun Jing, Chen Jason Zhang, Min Yang
机构
*
Shenzhen Key Laboratory for High Performance Data Mining(深圳高性能数据挖掘重点实验室)
;
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院)
;
Shenzhen University(深圳大学)
;
University of Science and Technology of China(中国科学技术大学)
;
PolyU(香港理工大学)
;
East China Normal University(华东师范大学)
;
Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology(深圳大学先进技术研究院人工智能研究所)
;
University of New South Wales(新南威尔士大学)
;
Anhui University(安徽大学)
机构
*
Information Hub, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)信息中心)
;
State Key Laboratory of Precision and Intelligent Chemistry, University of Science and Technology of China(中国科学技术大学精密与智能化学国家重点实验室)
;
State Key Laboratory of Physical Chemistry of Solid Surface, College of Chemistry and Chemical Engineering, Xiamen University(厦门大学化学系固态表面物理化学国家重点实验室)
;
The University of Hong Kong(香港大学)
;
Peking Union Medical College and Chinese Academy of Medical Sciences(北京协和医学院中国医学科学院)
;
The Hong Kong University of Science and Technology(香港科技大学)
;
Hunan University(湖南大学)
;
AI for Science Center, Shanghai Artificial Intelligence Laboratory(上海人工智能实验室人工智能科学中心)
MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM
MyGO-Splat:面向仅RGB高斯SLAM的多目标闭环几何反馈
Fan Zhu, Ziyu Chen, Zhenjun Zhao, Zhisong Xu, Hui Zhu, Mingrui Li, Chunmao Jiang, Javier Civera
机构
*
HFIPS, Chinese Academy of Sciences(中国科学院合肥智能机械研究所)
;
University of Science and Technology of China(中国科学技术大学)
;
Tohoku University(东北大学)
;
University of Zaragoza(阿斯图里亚大学)
;
University of Tokyo(东京大学)
;
Dalian University of Technology(大连理工大学)
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
SPADE-Bench:通过计划-行动分歧评估智能体中的自发性策略欺骗
Yuyan Bu, Haowei Li, Qirui Zheng, Bowen Dong, Kaiyue Yang, Jiaming Ji, Yingshui Tan, Wenxin Li, Yaodong Yang, Juntao Dai
机构
*
Beijing Academy of Artificial Intelligence(北京人工智能研究院)
;
Peking University(北京大学)
;
University of Science and Technology of China(中国科学技术大学)
;
University of Chinese Academy of Science(中国科学院大学)
;
Alibaba Group(阿里巴巴集团)
机构
*
Hong Kong University of Science and Technology (Guangzhou)(香港理工大学(广州))
;
Tsinghua University(清华大学)
;
Nanyang Technological University(南洋理工大学)
;
Renmin University of China(中国人民大学)
;
University of Science and Technology of China(中国科学技术大学)
;
University of Chinese Academy of Sciences(中国科学院大学)
Towards Realistic Open-Vocabulary Remote Sensing Segmentation: Benchmark and Baseline
迈向现实的开放词汇遥感分割:基准与基线
Bingyu Li, Tao Huo, Haocheng Dong, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li
机构
*
Department of Electronic Engineering and Information Science, University of Science and Technology of China(电子工程与信息科学系,中国科学技术大学)
;
School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University(人工智能学院,光学与电子学系(iOPEN),西北工业大学)
;
Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China(人工智能研究院(TeleAI),中国电信,中华人民共和国)
机构
*
University of Science and Technology of China(中国科学技术大学)
;
The Chinese University of Hong Kong, MMLAB(香港中文大学多媒体实验室)
;
JD Explore Academy(京东探索研究院)
;
Beihang University(北京航空航天大学)
机构
*
Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院(AIR))
;
Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University(清华大学交叉信息研究院(IIIS))
;
Nanjing University(南京大学)
;
University of Science and Technology of China(中国科学技术大学)
;
Microsoft Research Asia(微软亚洲研究院)
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
本体引导的反向思维使大语言模型在知识图谱问答中更强
Runxuan Liu, Bei Luo, Jiaqi Li, Baoxin Wang, Ming Liu, Dayong Wu, Shijin Wang, Bing Qin
机构
*
Harbin Institute of Technology(哈尔滨工业大学)
;
Beijing University of Posts and Telecommunications(北京邮电大学)
;
Joint Laboratory of HIT and iFLYTEK(哈工大与科大讯飞联合实验室)
;
University of Science and Technology of China(中国科学技术大学)
;
Pengcheng Laboratory(鹏城实验室)
机构
*
University of Science and Technology of China(中国科学技术大学)
;
Zhongguancun Academy(中关村学院)
;
Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院)
;
Shenzhen University(深圳大学)
;
Shanghai University of Finance and Economics(上海财经大学)
;
Tsinghua University(清华大学)
;
Fudan University(复旦大学)