参考来源

第 169–192 条，共 766 条来源

169. De novo design of protein structure and function with RFdiffusion

     Watson et al.
     2023-07-11

     来源定位: Abstract; conditional backbone generation, experimental characterization and limitations.

     查阅日期: 2026-10-22

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 可编程蛋白设计的闭环：从生成骨架到可测量功能的条件概率

170. Deciphering microbial interactions in synthetic human gut microbiome communities

     Ophelia S Venturelli; Alex V Carr; Garth Fisher; Ryan H Hsu; Rebecca Lau; Benjamin P Bowen; et al.
     2018-06-21

     来源定位: Abstract; Figs. 3–4; conditioned-media analysis

     核查范围: 合成群落和gLV建模；相互作用依赖环境。

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 从相关菌群到可控群落：微生物互作、组成数据与因果验证

171. Deduplicating Training Data Makes Language Models Better

     , , , , , ,
     2021-07-14

     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 (5)

     • 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
     • 数据去重与评测污染：从样本家族到可信泛化分数
     • 超越单一排行榜：能力测量、污染控制与统计不确定性
     • 检索增强生成的证据工程：召回误差、引用归因与端到端可信性
     • 合成训练数据的质量闭环：覆盖、筛选偏差与尾部信息流失

172. Deduplicating Training Data Makes Language Models Better

     Katherine Lee; Daphne Ippolito; Andrew Nystrom; Chiyuan Zhang; Douglas Eck; Chris Callison-Burch; Nicholas Carlini
     2022
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Data Multiplicity Is a Training Measure

173. Deduplicating Training Data Mitigates Privacy Risks in Language Models

     Nikhil Kandpal; Eric Wallace; Colin Raffel
     2022
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Data Multiplicity Is a Training Measure

174. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

     Ji Xin; Raphael Tang; Jaejun Lee; Yaoliang Yu; Jimmy Lin
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • The Price of Stopping Early: Adaptive Depth, Confidence, and the Systems Cost of Neural Decisions

175. Deep Double Descent: Where Bigger Models and More Data Hurt

     Preetum Nakkiran; Gal Kaplun; Yamini Bansal; Tristan Yang; Boaz Barak; Ilya Sutskever
     2019
     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

176. Deep Ensembles: A Loss Landscape Perspective

     Stanislav Fort; Huiyi Hu; Balaji Lakshminarayanan
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Many Models Share One Mistake: Error Correlation and Epistemic Signals in Deep Ensembles

177. Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram

     Biancalani et al.
     2021

     来源定位: Primary paper: mapping, shared genes and spatial alignment; associated author repository is linked by the paper.

     查阅日期: 2026-10-22

     打开原始来源 ↗
     引用本来源的文章 (1)

     • 从细胞表达到组织生态：空间组学模型的可辨识性、邻域尺度与验证

178. Deep learning perturbation models can outperform baselines on calibrated metrics

     Miller et al.
     2026-10-01

     来源定位: 14 datasets, 18 metrics; positive-control calibration, weighted errors and task-dependent conclusions.

     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

179. Deep Learning with Differential Privacy

     , , , , , ,
     2016-07-01

     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)

     • 联邦学习的隐私账本：加权聚合、裁剪噪声与安全聚合边界

180. Deep Learning with Differential Privacy

     Martín Abadi; Andy Chu; Ian Goodfellow; H. Brendan McMahan; Ilya Mironov; Kunal Talwar; Li Zhang
     2016
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Clipping Changes the Gradient Before Privacy Noise Arrives

181. Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii

     Liu et al.
     2023-05-25

     来源定位: Narrow-spectrum lead, LolE-related mechanism and mouse wound-model evidence; not a clinical approval.

     查阅日期: 2026-10-22

     打开原始来源 ↗
     引用本来源的文章 (1)

     • AI 抗生素发现的证据链：化学空间、可解释结构与临床前验证

182. Deep Reinforcement Learning from Human Preferences

     Paul F. Christiano; Jan Leike; Tom B. Brown; Miljan Martic; Shane Legg; Dario Amodei
     2017
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Preference Optimization Does Not Identify Human Utility

183. Deep Residual Learning for Image Recognition

     Kaiming He; Xiangyu Zhang; Shaoqing Ren; Jian Sun
     2015
     打开原始来源 ↗
     引用本来源的文章 (1)

     • When Depth Becomes a Dynamical System

184. Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines

     Ahlmann-Eltze et al.
     2025

     来源定位: Unseen and combination perturbation benchmarks; Methods specify model versions and evaluation.

     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

185. DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

     David Salinas; Valentin Flunkert; Jan Gasthaus
     2017
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Forecasts Must Respect the Clock: Temporal Leakage and Evaluation

186. DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

     , ,
     2019-10-08

     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)

     • 神经算子与偏微分方程：函数映射、频谱截断和物理误差

187. DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

     Lu Lu; Pengzhan Jin; George Em Karniadakis
     2019
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Learning an Operator Across Grids: Resolution, Aliasing, and What Transfers

188. Definitions: When is a build reproducible?

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

     • From Source to Artifact: Reproducible Builds and the Limits of Provenance

189. Denoising Diffusion Implicit Models

     Jiaming Song; Chenlin Meng; Stefano Ermon
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Diffusion Generation Through the Lens of Score Error

190. Denoising Diffusion Implicit Models

     Jiaming Song; Chenlin Meng; Stefano Ermon
     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

191. Denoising Diffusion Probabilistic Models

     , ,
     2020-06-19

     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

192. Denoising Diffusion Probabilistic Models

     Jonathan Ho; Ajay Jain; Pieter Abbeel
     2020
     打开原始来源 ↗
     引用本来源的文章 (1)

     • Diffusion Generation Through the Lens of Score Error