参考来源

第 73–96 条，共 766 条来源

73. Atlas: Few-shot Learning with Retrieval Augmented Language Models

    Gautier Izacard; Patrick Lewis; Maria Lomeli; Lucas Hosseini; Fabio Petroni; Timo Schick; Jane Dwivedi-Yu; Armand Joulin; Sebastian Riedel; Edouard Grave
    2022
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Retrieval Is Part of the Model: Exposure, Evidence, and Training-Time Coupling

74. Atomic Commit In SQLite

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

    • After the Power Fails: Crash Consistency and the Meaning of Durable

75. Atomic interferometry using stimulated Raman transitions

    Mark Kasevich; Steven Chu
    1991
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Matter Waves as Accelerometers: Scale Factors, Wavefronts and the Cost of Longer Interrogation

76. Attention Is All You Need

    Vaswani et al.
    2017-06-12

    来源定位: v7; sections 3-4; Table 2 (EN-DE only)

    核查范围: Transformer uses scaled dot-product attention; full attention has quadratic pair complexity. EN-DE big model 28.4 BLEU; no cross-version EN-FR claim.

    查阅日期: 2026-10-15

    打开原始来源 ↗
    引用本来源的文章 (5)

    • 机制可解释性的证据阶梯：叠加表示、干预与忠实性检验
    • 稀疏专家模型的真实成本：路由、容量约束与分布式通信
    • 推测解码的分布与成本：接受校正、残差采样和加速边界
    • 选择性状态空间模型：Mamba 的递推、扫描与记忆边界
    • 从注意力到 IO 感知执行：Transformer 的计算结构、复杂度与可复核分析

77. Attention Is All You Need

    Ashish Vaswani; Noam Shazeer; Niki Parmar; Jakob Uszkoreit; Llion Jones; Aidan N. Gomez; Lukasz Kaiser; Illia Polosukhin
    2017
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Rank Is Not a Capacity Certificate: Attention Bottlenecks Beyond the Score Matrix

78. Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

    Yihe Dong; Jean-Baptiste Cordonnier; Andreas Loukas
    2021
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Rank Is Not a Capacity Certificate: Attention Bottlenecks Beyond the Score Matrix

79. Attention is not Explanation

    ,
    2019-02-26

    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)

    • 机制可解释性的证据阶梯：叠加表示、干预与忠实性检验

80. AudioLM: A Language Modeling Approach to Audio Generation

    Zalán Borsos; Raphaël Marinier; Damien Vincent; Eugene Kharitonov; Olivier Pietquin; Matt Sharifi; Dominik Roblek; Olivier Teboul; David Grangier; Marco Tagliasacchi; Neil Zeghidour
    2023
    打开原始来源 ↗
    引用本来源的文章 (1)

    • What the Audio Tokens Carry: Neural Codecs, Generative Interfaces, and Latency Budgets

81. Augmented Neural ODEs

    Emilien Dupont; Arnaud Doucet; Yee Whye Teh
    2019
    打开原始来源 ↗
    引用本来源的文章 (1)

    • The Solver Is Part of the Network: Neural ODEs, Discrete Gradients, and Numerical Fidelity

82. Auto-Encoding Variational Bayes

    Diederik P. Kingma; Max Welling
    2013
    打开原始来源 ↗
    引用本来源的文章 (1)

    • When a Latent Variable Stops Carrying Information

83. Autonomous chemical research with large language models

    Boiko et al.
    2023-12-20

    来源定位: LLM orchestration of documentation, code and laboratory interfaces; demonstrated experiments have bounded scope.

    查阅日期: 2026-10-22

    打开原始来源 ↗
    引用本来源的文章 (1)

    • 自主实验室的科学闭环：主动学习、测量误判与可追溯发现

84. Autoregressive Image Generation using Residual Quantization

    Doyup Lee; Chiheon Kim; Saehoon Kim; Minsu Cho; Wook-Shin Han
    2022
    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

85. Avoiding fusion plasma tearing instability with deep reinforcement learning

    Seo et al.
    2024-02-21

    来源定位: DIII-D tearing-avoidance controller; model-based training and high-performance operational constraints.

    查阅日期: 2026-10-22

    打开原始来源 ↗
    引用本来源的文章 (1)

    • 聚变等离子体的学习控制：形状跟踪、撕裂回避与闭环可靠性

86. AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

    , , , , , , , , ,
    2023-06-01

    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)

    • 低比特推理的误差账本：量化尺度、校准与真实内存收益

87. Basis of Permeability/Selectivity Tradeoff Relations in Polymeric Gas Separation Membranes

    Benny D. Freeman
    1999
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Separating Molecules at Scale: Membrane Selectivity, Permeance and Process-Level Value

88. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

    Sergey Ioffe; Christian Szegedy
    2015
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Normalization Changes the Geometry of Learning

89. BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning

    Yeming Wen; Dustin Tran; Jimmy Ba
    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

90. Bayesian Deep Learning and a Probabilistic Perspective of Generalization

    Andrew Gordon Wilson; Pavel Izmailov
    2022
    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

91. BBR: congestion-based congestion control

    Neal Cardwell; Yuchung Cheng; C. Stephen Gunn; Soheil Hassas Yeganeh; Van Jacobson
    2017
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Congestion Control as Delayed Inference: Throughput, Queues, and Fairness

92. Beam Programming Guide

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

    • When a Stream Is Complete: Event Time, Watermarks, and Revisable Results

93. BEiT: BERT Pre-Training of Image Transformers

    Hangbo Bao; Li Dong; Songhao Piao; Furu Wei
    2021
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Reconstruction Is Not a Certificate of Semantic Understanding

94. Benign Overfitting in Linear Regression

    Peter L. Bartlett; Philip M. Long; Gábor Lugosi; Alexander Tsigler
    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

95. Better Performance at Lower Occupancy

    Vasily Volkov
    2010
    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

96. Beyond neural scaling laws: beating power law scaling via data pruning

    Ben Sorscher; Robert Geirhos; Shashank Shekhar; Surya Ganguli; Ari S. Morcos
    2022
    打开原始来源 ↗
    引用本来源的文章 (1)

    • Data Multiplicity Is a Training Measure