Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
通过局部分支路由实现高效且可训练的语言模型测试时扩展
Yutong Yin, Mingyu Jin, Jin Pan, Changyi Yang, Zijie Xia, Dhruv Pai, Shuming Hu, Zhen Zhang, Chenyang Zhao, Jinman Zhao, Wujiang Xu, Raymond Li, Xin Eric Wang, Julian McAuley, Zhaoran Wang
机构
*
Northwestern University(西北大学)
;
Rutgers University(罗格斯大学)
;
University of Wisconsin–Madison(威斯康星大学麦迪逊分校)
;
Carnegie Mellon University(卡内基梅隆大学)
;
LMSYS Org(LMSYS组织)
;
Tilde Research(Tilde研究)
;
University of California, Santa Barbara(加州大学圣塔芭芭拉分校)
;
University of Toronto(多伦多大学)
;
University of British Columbia(不列颠哥伦比亚大学)
;
University of California, San Diego(加州大学圣迭戈分校)
机构
*
AI Engineering, USA TODAY Co., Inc.(AI工程,USA TODAY公司)
;
School of Systems Science and Industrial Engineering, Binghamton University, State University of New York(系统科学与工业工程学院,宾夕法尼亚州立大学宾夕法尼亚州立大学)
;
Binghamton Center of Complex Systems, Binghamton University, State University of New York(宾夕法尼亚州立大学复杂系统中心)
;
Waseda Innovation Lab, Waseda University, Tokyo, Japan(早稻田大学创新实验室)
机构
*
School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院)
;
State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学自动化与智能感知学院海底科学国家重点实验室)
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
ToE:一种具有动态多源证据检索与聚合的分层可解释声明验证框架
Zhaoqi Wang, Zijian Zhang, Kun Zheng, Zhen Li, Xin Li, Chunlei Li, Jiamou Liu
机构
*
School of Cyberspace Science and Technology, Beijing Institute of Technology(北京理工大学信息科学与技术学院)
;
TravelSky Technology Limited(TravelSky技术有限公司)
;
School of Computer Science, University of Auckland(奥克兰大学计算机科学学院)
专题命中
规划决策
:agent(abstract);分类 cs.AI
AI总结
提出Tree of Evidence (ToE)框架,通过强化学习驱动的多源检索、证据评估和参数树聚合,实现可解释的自动事实核查,在多个数据集上提升4-24个百分点,尤其对抗性毒化输入效果显著。
A Generalization Theory for JEPA-Based World Models
基于JEPA的世界模型的泛化理论
Jingyi Cui, Qi Zhang, Hongwei Wen, Yisen Wang
机构
*
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室)
;
University of Sydney(悉尼大学)
机构
*
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院)
;
Department of Networked Intelligence, Peng Cheng Laboratory(鹏城实验室网络智能部)
;
School of Computer Science and Engineering, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算机科学与工程学院)
TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation
TAVR-VLM:面向抗幻觉报告生成的风险条件因果基础
Zhixiang Lu, Xiwei Liu, Sifan Song, Changkai Ji, Anh Nguyen, Jionglong Su, Imran Razzak, Jinfeng Wang
机构
*
Xi’an Jiaotong-Liverpool University(西交利物浦大学)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
Shanghai Jiao Tong University(上海交通大学)
;
University of Liverpool(利物浦大学)
;
Kunming University of Science and Technology(昆明理工大学)
Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute
灵活功率的AI数据中心:一种电网响应式计算的新范式
Chris Williams, Philip Colangelo, Ayse Coskun, Ethan Levine, Andy Neale, Ciaran Roberts, Shayan Sengupta, Nikhil Shirolkar, Varun Sivaram, Sarah Soares, Ethan Tiao, Scott Underwood, Daniel Wilson, Frank Sharp, Luke Wainwright, Harry Petty, Scott Wallace, Brandon Records
机构
*
Emerald AI
;
Electric Power Research Institute (EPRI)(电力研究研究院)
;
National Grid(国家电网)
;
NVIDIA
;
Oracle
Learning Optimization Proxies for Sequential Contextual Stochastic Programs: An Order Fulfillment Application
学习序列上下文随机程序的优化代理:订单履行应用
Tinghan Ye, Shuaicheng Tong, Changkun Guan, Beste Basciftci, Pascal Van Hentenryck
机构
*
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(佐治亚理工学院工业与系统工程系)
;
Tippie College of Business, University of Iowa(爱荷华大学蒂普皮商学院)
机构
*
school of Physics, Engineering and Technology, University of York(物理、工程与技术学院,约克大学)
;
Radio Systems Research, Nokia Bell Labs(诺基亚贝尔实验室无线电系统研究部)
;
School of Electrical and Electronic Engineering, University of Sheffield(电子与电气工程学院,谢菲尔德大学)
;
Bradley Department of Electrical and Computer Engineering, Virginia Tech(布拉德利电气与计算机工程系,弗吉尼亚理工学院)
VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
VeryTrace: 通过可编译形式化与结构化验证验证推理轨迹
Ninghan Zhong, Ahmet Ege Tanriverdi, Kaan Kale, Sriram Vishwanath
机构
*
School of Electrical and Computer Engineering, Georgia Institute of Technology, USA(佐治亚理工学院电子与计算机工程学院)
;
Department of Electrical and Computer Engineering, Bogazici University, Turkey(博亚奇大学电子与计算机工程系)
Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences
FLKit的设计与开发:面向健康与生命科学中联邦学习的结构化入门工具包
Ashkan Pirmani, Ilse Vermeulen, Goran Vinterhalter, Lotte Geys, Axel Faes, Muhammad Quamber Ali, Nishkala Sattanathan, Geert Vandeweyer, Yves Moreau, Liesbet M. Peeters
机构
*
STADIUS, Department of Electrical Engineering (ESAT), KU Leuven(STADIUS部门,电气工程系(ESAT),鲁汶大学)
;
Biomedical Research Institute (BIOMED), Hasselt University(生物医学研究所(BIOMED),哈塞尔特大学)
;
Data Science Institute (DSI), Hasselt University(数据科学研究所(DSI),哈塞尔特大学)
;
Department of Medical Genetics, University of Antwerp(医学遗传学系,安特卫普大学)