参考来源

第 577–600 条，共 766 条来源

577. RoFormer: Enhanced Transformer with Rotary Position Embedding

     Jianlin Su; Yu Lu; Shengfeng Pan; Ahmed Murtadha; Bo Wen; Yunfeng Liu
     2021
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Beyond the Training Window: Position, Distance, and Extrapolation in Transformers

578. Roofline Performance Model

     NERSC
     2026
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Beyond Peak FLOPS: GPU Performance as a Sequence of Resource Constraints

579. Roofline: An Insightful Visual Performance Model for Floating-Point Programs and Multicore Architectures

     Samuel Webb Williams; Andrew Waterman; David A. Patterson
     2008
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Beyond Peak FLOPS: GPU Performance as a Sequence of Resource Constraints

580. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

     , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , --------------------------------------------------------------------------------
     2023-07-28

     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)

     • 扩散策略与机器人闭环：多模态动作、执行时限与安全验证

581. Rényi Differential Privacy

     Ilya Mironov
     2017
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Privacy Budgets Under Composition: Accounting for Repeated Statistical Release

582. SAM 2: Segment Anything in Images and Videos

     , , , , , , , , , , , , , , , , , L12: View a PDF of the paper titled SAM 2: Segment Anything in Images and Videos, by Nikhila Ravi and 17 other authors
     2024-08-01

     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)

     • 可提示分割与视频记忆：SAM 接口、掩码歧义和跨域验证

583. Sampling

     OpenTelemetry Authors
     2025
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Seeing a Distributed Execution: Sampling, Context, and the Limits of Trace Evidence

584. SAND: Towards High-Performance Serverless Computing

     Istemi Ekin Akkus; Ruichuan Chen; Ivica Rimac; Manuel Stein; Klaus Satzke; Andre Beck; Paarijaat Aditya; Volker Hilt
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Serverless Is a Placement Decision: Cold Starts, Isolation, and State

585. Sanity Checks for Saliency Maps

     Julius Adebayo; Justin Gilmer; Michael Muelly; Ian Goodfellow; Moritz Hardt; Been Kim
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • What an Interpretable Feature Actually Establishes

586. Satellite-based estimates of groundwater depletion in India

     Matthew Rodell; Isabella Velicogna; James S. Famiglietti
     2009
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Water Returns but Storage Does Not: Groundwater Depletion and Irreversible Compaction

587. Scalable, transparent, and post-quantum secure computational integrity

     Eli Ben-Sasson; Iddo Bentov; Yinon Horesh; Michael Riabzev
     2018
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Succinct Proofs, Substantial Costs: Evaluating Zero-Knowledge Systems End to End

588. Scalable-manufactured randomized glass-polymer hybrid metamaterial for daytime radiative cooling

     Yao Zhai; Yaoguang Ma; Sabrina N. David; Dongliang Zhao; Runnan Lou; Gang Tan; Ronggui Yang; Xiaobo Yin
     2017
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Cooling beneath the Sky: Spectral Selectivity, Atmospheric Windows and System Boundaries

589. Scaling Data-Constrained Language Models

     Niklas Muennighoff; Alexander M. Rush; Boaz Barak; Teven Le Scao; Aleksandra Piktus; Nouamane Tazi; Sampo Pyysalo; Thomas Wolf; Colin Raffel
     2023
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Data Multiplicity Is a Training Measure

590. Scaling deep learning for materials discovery

     Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, Gowoon Cheon, Ekin Dogus Cubuk
     2023-11-29

     来源定位: Abstract; Active learning; Discovered stable crystals; Methods

     核查范围: Nature 624, 80–85 (2023), DOI 10.1038/s41586-023-06735-9。预测/计算稳定性、合成与应用验证分别讨论；本文没有新增合成实验。

     查阅日期: 2026-10-21

     打开原始来源 ↗
     引用本来源的文章 (2)

     • AI 材料发现的证据链：势能模型、凸包与合成验证
     • 自主实验室的科学闭环：主动学习、测量误判与可追溯发现

591. Scaling Instruction-Finetuned Language Models

     Chung et al.
     2022-10-20

     来源定位: abstract; historical 2022 research

     核查范围: Instruction finetuning studies task mixtures, scale and chain-of-thought data; training loss and instruction utility are different objectives.

     查阅日期: 2026-10-15

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 计算最优语言模型：缩放律、数据配比与受预算约束的训练决策

592. Scaling Laws for Neural Language Models

     Jared Kaplan; Sam McCandlish; Tom Henighan; Tom B. Brown; Benjamin Chess; Rewon Child; Scott Gray; Alec Radford; Jeffrey Wu; Dario Amodei
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Compute-Optimal Learning Depends on the Accounting

593. Scaling Laws for Neural Language Models

     Kaplan et al.
     2020-01-23

     来源定位: v1; sections 1 and 6

     核查范围: Empirical loss scaling and a compute allocation analysis under its particular setup; not a universal law of downstream abilities.

     查阅日期: 2026-10-15

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 计算最优语言模型：缩放律、数据配比与受预算约束的训练决策

594. scGPT: toward building a foundation model for single-cell multi-omics using generative AI

     Cui et al.
     2024

     来源定位: Single-cell pretraining and downstream adaptation; not a universal causal simulator.

     查阅日期: 2026-10-22

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 虚拟细胞能预测什么：扰动基础模型、线性基线与评价指标的校准

595. Score-Based Generative Modeling through Stochastic Differential Equations

     , , , , ,
     2020-11-26

     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)

     • 扩散生成的概率路径：噪声预测、采样误差与潜空间建模

596. Score-Based Generative Modeling through Stochastic Differential Equations

     Yang Song; Jascha Sohl-Dickstein; Diederik P. Kingma; Abhishek Kumar; Stefano Ermon; Ben Poole
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Diffusion Generation Through the Lens of Score Error

597. Score-Based Generative Modeling through Stochastic Differential Equations

     Yang Song; Jascha Sohl-Dickstein; Diederik P. Kingma; Abhishek Kumar; Stefano Ermon; Ben Poole
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Guidance Changes the Target: Conditional Diffusion Between Fidelity and Concentration

598. SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

     Fabian B. Fuchs; Daniel E. Worrall; Volker Fischer; Max Welling
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Handedness Is Information: Molecular Equivariance Beyond Distances

599. Search-and-replace genome editing without double-strand breaks or donor DNA

     Andrew V. Anzalone; Peyton B. Randolph; Jessie R. Davis; Alexander A. Sousa; Luke W. Koblan; Jonathan M. Levy; et al.
     2019-10-21

     来源定位: Abstract; Figs. 1–5

     核查范围: 建立引导RNA编码改写与逆转录机制；限原研究细胞体系。

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 引导编辑的精度账本：从序列改写到完整基因组结果的证据

600. Secure Aggregation Protocols

     Flower Labs
     2026
     打开原始来源 ↗
     引用本来源的文章 (1)

     • A Sum without Its Summands: Secure Aggregation under Dropout and Collusion