参考来源

第 649–672 条，共 766 条来源

649. Stochastic Gradient Descent as Approximate Bayesian Inference

     Stephan Mandt; Matthew D. Hoffman; David M. Blei
     2017
     打开原始来源 ↗
     引用本来源的文章 (1)

     • What Gradient Noise Actually Controls

650. Structured Denoising Diffusion Models in Discrete State-Spaces

     Jacob Austin; Daniel D. Johnson; Jonathan Ho; Daniel Tarlow; Rianne van den Berg
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • What a Mask Forgets: Discrete Diffusion, Joint Dependence, and Parallel Token Generation

651. Subsampled Renyi Differential Privacy and Analytical Moments Accountant

     Yu-Xiang Wang; Borja Balle; Shiva Prasad Kasiviswanathan
     2019
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Clipping Changes the Gradient Before Privacy Noise Arrives

652. Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates

     Taku Kudo
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Tokens Are Not Units of Meaning: Probability Accounting Across Segmentations

653. Superconductivity in an infinite-layer nickelate

     Danfeng Li; Kyuho Lee; Bai Yang Wang; Motoki Osada; Samuel Crossley; Hye Ryoung Lee; Yi Cui; Yasuyuki Hikita; Harold Y. Hwang
     2019
     打开原始来源 ↗
     引用本来源的文章 (1)

     • A Superconducting Signature Is a Chain of Evidence: Nickelates, Interfaces and Competing Explanations

654. Suppression of RNA Recognition by Toll-like Receptors: The Impact of Nucleoside Modification and the Evolutionary Origin of RNA

     Katalin Karikó; Michael Buckstein; Houping Ni; Drew Weissman
     2005
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Beyond Encapsulation: The Multistage Transport Problem of Messenger RNA Delivery

655. Surprises in High-Dimensional Ridgeless Least Squares Interpolation

     Trevor Hastie; Andrea Montanari; Saharon Rosset; Ryan J. Tibshirani
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Fitting Noise Is Benign: Interpolation, Effective Rank, and the Geometry of Prediction

656. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

     Ze Liu; Yutong Lin; Yue Cao; Han Hu; Yixuan Wei; Zheng Zhang; Stephen Lin; Baining Guo
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Where Vision Transformers Put Their Inductive Bias

657. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

     , ,
     2021-01-11

     来源定位: Abstract; 原文方法、理论和实验章节见作者原始论文链接

     核查范围: 一手论文；原文研究归属原作者。本文的推导示例与建议实验方案另行标注，不冒充原论文或本站实测。

     查阅日期: 2026-10-21

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 稀疏专家模型的真实成本：路由、容量约束与分布式通信

658. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

     William Fedus; Barret Zoph; Noam Shazeer
     2022
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Sparse Experts Under Capacity and Routing Constraints

659. Syntax-Guided Synthesis

     Rajeev Alur; Rastislav Bodik; Garvit Juniwal; Milo M. K. Martin; Mukund Raghothaman; Sanjit A. Seshia; Rishabh Singh; Armando Solar-Lezama; Emina Torlak; Abhishek Udupa
     2013
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Programs from Counterexamples: Synthesis, Specifications, and Oracle Limits

660. Systematic evaluation of an atomic clock at 2 × 10−18 total uncertainty

     T.L. Nicholson; S.L. Campbell; R.B. Hutson; G.E. Marti; B.J. Bloom; R.L. McNally; W. Zhang; M.D. Barrett; M.S. Safronova; G.F. Strouse; W.L. Tew; J. Ye
     2015
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Time as a Measured Field: Optical Clock Networks, Correlated Errors and Relativistic Geodesy

661. Taming Transformers for High-Resolution Image Synthesis

     Patrick Esser; Robin Rombach; Björn Ommer
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Before the Generator Learns: Visual Tokenization, Information Bottlenecks, and Sequence Cost

662. Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting

     Bryan Lim; Sercan O. Arik; Nicolas Loeff; Tomas Pfister
     2019
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Forecasts Must Respect the Clock: Temporal Leakage and Evaluation

663. Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds

     Nathaniel Thomas; Tess Smidt; Steven Kearnes; Lusann Yang; Li Li; Kai Kohlhoff; Patrick Riley
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Handedness Is Information: Molecular Equivariance Beyond Distances

664. Tensor Programs II: Neural Tangent Kernel for Any Architecture

     Greg Yang
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Beyond a Frozen Tangent: What Kernel Limits Explain about Neural Feature Learning

665. Tent: Fully Test-time Adaptation by Entropy Minimization

     Dequan Wang; Evan Shelhamer; Shaoteng Liu; Bruno Olshausen; Trevor Darrell
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Inference Updates the Model: Test-Time Adaptation, Confidence, and State Drift

666. Terminology for Post-Quantum Traditional Hybrid Schemes

     Florence Driscoll; Michael Parsons; Britta Hale
     2025
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Replacing a Primitive Is Not Migrating a Protocol: Post-Quantum Key Establishment

667. Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization

     Yusuke Iwasawa; Yutaka Matsuo
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Inference Updates the Model: Test-Time Adaptation, Confidence, and State Drift

668. Textbooks Are All You Need

     , , , , , , , , , , , , , , , , , , L12: View a PDF of the paper titled Textbooks Are All You Need, by Suriya Gunasekar and 18 other authors
     2023-06-20

     来源定位: Abstract; 原文方法、理论和实验章节见作者原始论文链接

     核查范围: 一手论文；原文研究归属原作者。本文的推导示例与建议实验方案另行标注，不冒充原论文或本站实测。

     查阅日期: 2026-10-21

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 合成训练数据的质量闭环：覆盖、筛选偏差与尾部信息流失

669. The Benefits of Mixup for Feature Learning

     Difan Zou; Yuan Cao; Yuanzhi Li; Quanquan Gu
     2023
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Interpolation Changes the Learning Distribution

670. The Case for Learned Index Structures

     Tim Kraska; Alex Beutel; Ed H. Chi; Jeffrey Dean; Neoklis Polyzotis
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Learned Indexes Under Distribution Change: Prediction, Search, and Correctness

671. The complete sequence of a human genome

     Sergey Nurk; Sergey Koren; Arang Rhie; Mikko Rautiainen; Andrey V. Bzikadze; Alla Mikheenko; et al.
     2022-04

     来源定位: Abstract; genome assembly results

     核查范围: 完整单一参考与群体多样性覆盖是不同目标。

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 谁的基因组作为坐标：泛基因组、变异发现与参考偏差的可测量性

672. The Curse of Recursion: Training on Generated Data Makes Models Forget

     Ilia Shumailov; Zakhar Shumaylov; Yiren Zhao; Yarin Gal; Nicolas Papernot; Ross Anderson
     2023
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Recursive Synthetic Data and the Fate of Rare Support