Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
从测试时缩放的视角理解在线策略蒸馏
Xinmu Ge, Zizhuo Zhang, Yu Huang, Jianing Zhu, Lin Yuan, Wanli Gu, Weichang Wu, Weiran Huang, Xiaolu Zhang, Bo Han, Jun Zhou, Jiangchao Yao
机构
*
Hong Kong Baptist University(香港浸会大学)
;
University of Texas at Austin(德克萨斯大学奥斯汀分校)
;
Shanghai Jiao Tong University(上海交通大学)
;
Shanghai Innovation Institute(上海创新研究院)
;
Ant Group(蚂蚁集团)
Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning
裁决式字幕生成:用于严格零样本图像字幕生成的多智能体对齐评分与共识蒸馏束仲裁
Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu, Ngo Tan Vu Khanh
机构
*
AI Platform OneNexus, OneMount(OneMount AI平台OneNexus)
;
School of Electronic Engineering, Soongsil University(崇实大学电子工程学院)
;
MoAdata(MoAdata公司)
;
University of Economics Ho Chi Minh City (UEH)(胡志明市经济大学)
机构
*
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
INSAIT, Sofia University “St. Kliment Ohridski”(索非亚大学“圣克莱门特·奥赫里德斯基”INSAIT学院)
;
University of Arizona(亚利桑那大学)
;
FMI, Sofia University “St. Kliment Ohridski”(索非亚大学“圣克莱门特·奥赫里德斯基”FMI学院)
;
The Fin AI(The Fin AI公司)
;
The University of Tokyo(东京大学)
;
Linköping University(林雪平大学)
;
McGill University(麦吉尔大学)
;
Mila, Quebec AI Institute(魁北克Mila人工智能研究所)
;
Meiji Gakuin University(明治学院大学)
Lookahead Branching for Neural Network Verification
神经网络验证中的前瞻分支
Liam Davis, Duo Zhou, Huan Zhang, Guy Katz, Clark Barrett, Haoze Wu
机构
*
Amherst College(阿默斯特学院)
;
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
Hebrew University of Jerusalem(耶路撒冷希伯来大学)
;
Stanford University(斯坦福大学)
Distilled Reinforcement Learning for LLM Post-training
用于大语言模型训练后处理的蒸馏强化学习
Chen Wang, Zhaochun Li, Jionghao Bai, Yining Zhang, Hexuan Deng, Ge Lan, Yue Wang
机构
*
College of Elite Engineers, Nankai University(南开大学精英工程师学院)
;
Zhongguancun Academy(中关村学院)
;
Beijing Institute of Technology(北京理工大学)
;
Zhejiang University(浙江大学)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
Harbin Institute of Technology(哈尔滨工业大学)
;
College of Software, Nankai University(南开大学软件学院)
Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning
贝叶斯深度学习中的校准无采样不确定性估计
Tobias Jan Wieczorek, Leon de Andrade, Thomas Möllenhoff, Marcus Rohrbach
机构
*
TU Darmstadt & hessian.AI, Darmstadt, Germany(达姆施塔特工业大学 & hessian.AI,德国达姆施塔特)
;
RIKEN Center for Advanced Intelligence Project, Tokyo, Japan(日本理化学研究所革新智能研究中心,日本东京)