Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
使用扩散模型和循环推理机在像素空间中进行强引力透镜后验采样
Guillaume Payeur, Laurence Perreault-Levasseur, Gabriel Missael Barco, Yashar Hezaveh
机构
*
Department of Physics, Universit\'e de Montr\'eal, Montreal QC, Canada
;
Mila - Quebec AI Institute, Montreal QC, Canada
;
Ciela Institute, Institute for Astrophysics
;
Trottier Space Institute, McGill University, Montreal QC, Canada
;
Center for Computational Astrophysics, Flatiron Institute, New York, USA
;
Perimeter Institute for Theoretical Physics, Waterloo ON, Canada
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
基于高斯过程的后验采样强化学习用于连续控制:无界状态空间的次线性遗憾界
Hamish Flynn, Joe Watson, Ingmar Posner, Jan Peters
机构
*
University of Oxford(牛津大学)
;
Carnegie Mellon University(卡内基梅隆大学)
;
Technical University of Darmstadt(达姆施塔特技术大学)
;
Robotics Institute Germany(德国机器人研究所)
机构
*
University of Yamanashi(山梨大学)
;
Beijing Institute of Technology, Zhuhai(北京理工大学(珠海))
;
Shenzhen University(深圳大学)
;
Nagoya University(名古屋大学)
;
Osaka University(大阪大学)
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
神经网络的部分融合:集成与权重聚合之间的高效权衡
Fabian Morelli, Stephan Eckstein
机构
*
Department of Mathematics, University of Tübingen, Germany(图宾根大学数学系,德国)
;
Department of Computer Science, University of Tübingen, Germany(图宾根大学计算机科学系,德国)
Understanding Self-Supervised Learning via Latent Distribution Matching
通过潜在分布匹配理解自监督学习
Fabian A Mikulasch, Friedemann Zenke
机构
*
Friedrich Miescher Institute for Biomedical Research, 4056 Basel, Switzerland(弗里德里希·迈斯彻生物医学研究所)
;
Faculty of Science, University of Basel, 4033 Basel, Switzerland(巴塞尔大学科学学院)
Large Language Models Explore by Latent Distilling
通过潜在蒸馏探索大语言模型
Yuanhao Zeng, Ao Lu, Lufei Li, Zheng Zhang, Yexin Li, Kan Ren
机构
*
State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China(人工智能通用基础理论国家重点实验室,BIGAI,北京,中国)
;
School of Information Science and Technology, ShanghaiTech University, Shanghai, China(信息科学与技术学院,上海交通大学,上海,中国)
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
反向思维链生成中的事后合理化测量与缓解
Guangyue Peng, Zongchao Chen, Wen Luo, Yuntao Wen, Wei Li, Ruixiang Feng, Ran Le, Chen Yang, Zhenwei An, Yang Song, Tao Zhang, Houfeng Wang
机构
*
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(信息处理国家重点实验室,计算机科学学院,北京大学)
;
University of Electronic Science and Technology of China(电子科技大学)
;
Nanbeige Lab, BOSS Zhipin(纳贝格实验室,BOSS智联)
机构
*
Guangzhou University(广州大学)
;
Institue of Automation Chinese Academy of Sciences(中国科学院自动化研究所)
;
ByteDance Inc.(字节跳动公司)
;
University of Science and Technology Beijing(北京科技大学)