Reference sources

References 697–720 of 766

697. Toolformer: Language Models Can Teach Themselves to Use Tools

     Schick et al.
     2023-02-09

     Source location: abstract; training tool-use behavior

     Source scope: A self-supervised procedure selects useful API calls for training; training tool syntax does not establish production authorization.

     Inspected on: 2026-10-15

     Open original source ↗
     Referenced in (1)

     • 工具型 Agent 的可靠性：行动状态机、幂等语义与结果归因

698. Towards a general-purpose foundation model for computational pathology

     Richard J. Chen; Tong Ding; Ming Y. Lu; Drew F. K. Williamson; Guillaume Jaume; Andrew H. Song; Bowen Chen; Andrew Zhang; Daniel Shao; Muhammad Shaban; Mane Williams; Lukas Oldenburg; Luca L. Weishaupt; Judy J. Wang; Anurag Vaidya; Long Phi Le; Georg Gerber; Sharifa Sahai; Walt Williams; Faisal Mahmood
     2024
     Open original source ↗
     Referenced in (1)

     • From Slides to Sites: Foundation Models, Distribution Shift and Histopathology Validation

699. Towards Causal Representation Learning

     Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio
     2021-02-22

     Source location: Abstract and sections on interventions, independent mechanisms and causal representations

     Source scope: 原始论文PDF及作者书目信息已核对；因果识别条件不等于相关性预测。

     Inspected on: 2026-10-21

     Open original source ↗
     Referenced in (2)

     • 从相关到干预：AI 因果推断中的识别、混杂与可迁移性
     • 读懂非编码基因组：长程调控模型的尺度、变异效应与因果识别

700. Towards Causal Representation Learning

     Bernhard Schölkopf; Francesco Locatello; Stefan Bauer; Nan Rosemary Ke; Nal Kalchbrenner; Anirudh Goyal; Yoshua Bengio
     2021
     Open original source ↗
     Referenced in (1)

     • Interventions Do Not Name Latents: Causal Representation and Identifiability

701. Towards Deep Learning Models Resistant to Adversarial Attacks

     , , , ,
     2017-06-19

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

     Source scope: 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。

     Inspected on: 2026-10-21

     Open original source ↗
     Referenced in (1)

     • 对抗鲁棒性的可检验边界：威胁模型、范数预算与攻击验收

702. Towards Deep Learning Models Resistant to Adversarial Attacks

     Aleksander Madry; Aleksandar Makelov; Ludwig Schmidt; Dimitris Tsipras; Adrian Vladu
     2018
     Open original source ↗
     Referenced in (1)

     • Robustness Claims Need an Explicit Threat Model

703. Towards Making Systems Forget with Machine Unlearning

     Yinzhi Cao; Junfeng Yang
     2015
     Open original source ↗
     Referenced in (1)

     • What an Unlearning Test Can Actually Certify

704. Towards practical, high-capacity, low-maintenance information storage in synthesized DNA

     Nick Goldman; Paul Bertone; Siyuan Chen; Christophe Dessimoz; Emily M. LeProust; Botond Sipos; Ewan Birney
     2013
     Open original source ↗
     Referenced in (1)

     • An Archive Made of Molecules: DNA Data Storage, Erasures and End-to-End Reliability

705. Towards Stable Test-Time Adaptation in Dynamic Wild World

     Shuaicheng Niu; Jiaxiang Wu; Yifan Zhang; Zhiquan Wen; Yaofo Chen; Peilin Zhao; Mingkui Tan
     2023
     Open original source ↗
     Referenced in (1)

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

706. Towards the ground state of molecules via diffusion Monte Carlo on neural networks

     Ren et al.
     2023-03-31

     Source location: Trial wavefunctions and fixed-node diffusion Monte Carlo; total versus relative energy and nodal limitations.

     Inspected on: 2026-10-22

     Open original source ↗
     Referenced in (1)

     • 神经波函数的第一性原理：反对称性、变分上界与相关采样误差

707. Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

     Zeyuan Allen-Zhu; Yuanzhi Li
     2023
     Open original source ↗
     Referenced in (1)

     • Learning from a Moving Teacher: Self-Distillation, Temporal Smoothing, and Collapse Boundaries

708. Toy Models of Superposition

     , , , , , , , , , , , , , , ,
     2022-09-21

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

     Source scope: 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。

     Inspected on: 2026-10-21

     Open original source ↗
     Referenced in (1)

     • 机制可解释性的证据阶梯：叠加表示、干预与忠实性检验

709. Toy Models of Superposition

     Nelson Elhage; Tristan Hume; Catherine Olsson; Nicholas Schiefer; Tom Henighan; Shauna Kravec; Zac Hatfield-Dodds; Robert Lasenby; Dawn Drain; Carol Chen; Roger Grosse; Sam McCandlish; Jared Kaplan; Dario Amodei; Martin Wattenberg; Christopher Olah
     2022
     Open original source ↗
     Referenced in (1)

     • What an Interpretable Feature Actually Establishes

710. Trace Context

     W3C Distributed Tracing Working Group
     2021
     Open original source ↗
     Referenced in (1)

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

711. Tracking the Evolution of Non–Small-Cell Lung Cancer

     Mariam Jamal-Hanjani; Gareth A. Wilson; Nicholas McGranahan; Nicolai J. Birkbak; Thomas B.K. Watkins; Selvaraju Veeriah; Seema Shafi; Diana H. Johnson; Richard Mitter; Rachel Rosenthal; Max Salm; Stuart Horswell; Mickael Escudero; Nik Matthews; Andrew Rowan; Tim Chambers; David A. Moore; Samra Turajlic; Hang Xu; Siow-Ming Lee; Martin D. Forster; Tanya Ahmad; Crispin T. Hiley; Christopher Abbosh; Mary Falzon; Elaine Borg; Teresa Marafioti; David Lawrence; Martin Hayward; Shyam Kolvekar; Nikolaos Panagiotopoulos; Sam M. Janes; Ricky Thakrar; Asia Ahmed; Fiona Blackhall; Yvonne Summers; Rajesh Shah; Leena Joseph; Anne M. Quinn; Phil A. Crosbie; Babu Naidu; Gary Middleton; Gerald Langman; Simon Trotter; Marianne Nicolson; Hardy Remmen; Keith Kerr; Mahendran Chetty; Lesley Gomersall; Dean A. Fennell; Apostolos Nakas; Sridhar Rathinam; Girija Anand; Sajid Khan; Peter Russell; Veni Ezhil; Babikir Ismail; Melanie Irvin-Sellers; Vineet Prakash; Jason F. Lester; Malgorzata Kornaszewska; Richard Attanoos; Haydn Adams; Helen Davies; Stefan Dentro; Philippe Taniere; Brendan O’Sullivan; Helen L. Lowe; John A. Hartley; Natasha Iles; Harriet Bell; Yenting Ngai; Jacqui A. Shaw; Javier Herrero; Zoltan Szallasi; Roland F. Schwarz; Aengus Stewart; Sergio A. Quezada; John Le Quesne; Peter Van Loo; Caroline Dive; Allan Hackshaw; Charles Swanton
     2017
     Open original source ↗
     Referenced in (1)

     • The Tumor Is Not a Sample: Spatial Evolution, Detection Limits and Longitudinal Inference

712. Train faster, generalize better: Stability of stochastic gradient descent

     Moritz Hardt; Benjamin Recht; Yoram Singer
     2016
     Open original source ↗
     Referenced in (1)

     • What One Replaced Example Changes: Algorithmic Stability, Training Time, and Generalization

713. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

     , ,
     2021-08-27

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

     Source scope: 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。

     Inspected on: 2026-10-21

     Open original source ↗
     Referenced in (1)

     • 位置编码与长上下文：旋转相位、距离偏置和有效信息使用

714. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

     Ofir Press; Noah A. Smith; Mike Lewis
     2021
     Open original source ↗
     Referenced in (1)

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

715. Training Compute-Optimal Large Language Models

     Hoffmann et al.
     2022-03-29

     Source location: v1; section 3 and section 4

     Source scope: Under fixed training compute their fitted frontier scales parameters and training tokens approximately equally. Chinchilla has 70B parameters trained on 1.4T tokens.

     Inspected on: 2026-10-15

     Open original source ↗
     Referenced in (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

716. Training Compute-Optimal Large Language Models

     Jordan Hoffmann; Sebastian Borgeaud; Arthur Mensch; Elena Buchatskaya; Trevor Cai; Eliza Rutherford; Diego de Las Casas; Lisa Anne Hendricks; Johannes Welbl; Aidan Clark; Tom Hennigan; Eric Noland; Katie Millican; George van den Driessche; Bogdan Damoc; Aurelia Guy; Simon Osindero; Karen Simonyan; Erich Elsen; Jack W. Rae; Oriol Vinyals; Laurent Sifre
     2022
     Open original source ↗
     Referenced in (1)

     • Compute-Optimal Learning Depends on the Accounting

717. Training data-efficient image transformers & distillation through attention

     Hugo Touvron; Matthieu Cord; Matthijs Douze; Francisco Massa; Alexandre Sablayrolles; Hervé Jégou
     2021
     Open original source ↗
     Referenced in (1)

     • Where Vision Transformers Put Their Inductive Bias

718. Training language models to follow instructions with human feedback

     Ouyang et al.
     2022-03-04

     Source location: v1; method and limitations

     Source scope: Demonstrations, preference reward learning and RL optimization form the reported InstructGPT pipeline; preference depends on the sampled prompt and labeler population.

     Inspected on: 2026-10-15

     Open original source ↗
     Referenced in (1)

     • 偏好优化的目标边界：奖励代理、参考策略与分布漂移

719. Transfer learning enables predictions in network biology

     Theodoris et al.
     2023-05-31

     Source location: Pretraining, context-dependent representations and in silico perturbations.

     Inspected on: 2026-10-22

     Open original source ↗
     Referenced in (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

720. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

     Angelos Katharopoulos; Apoorv Vyas; Nikolaos Pappas; François Fleuret
     2020
     Open original source ↗
     Referenced in (1)

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