{ "source_file": "0930", "source_platform": "研究机构", "author": "Stanford CS224n", "title_listed": "Stanford CS224n（NLP with Deep Learning）", "keywords": "NLP,深度学习,Transformer", "domain": "NLP", "content_type": "课程", "is_paid_flag": "否", "url": "https://web.stanford.edu/class/cs224n/", "publish_date": "持续更新", "corpus_stage": "文本处理", "notes": "斯坦福 NLP 课程", "id": "aa5b9c1e53d2", "collected_at": "2026-10-02T17:02:35", "title": "Stanford CS 224N | Natural Language Processing with Deep Learning", "body_markdown": "CS224N: Natural Language Processing with Deep Learning\nStanford / Winter 2026\nNatural language processing (NLP) is a crucial part of artificial intelligence (AI), modeling how people share information.\n In recent years, deep learning approaches have obtained very high performance on many NLP tasks.\n In this course, students gain a thorough introduction to cutting-edge neural networks for NLP.\nInstructors\nDiyi Yang\nYejin Choi\nCourse Staff\nJohn Cho (Course Manager)\nSwati Dube Batra (Course Manager Advisor)\nTeaching Assistants\nJulie Kallini (Head TA)\nAhmed Ahmed\nDavid Anugraha\nLuke Bailey\nSarah Chen\nCaroline Choi\nAdvit Deepak\nNevin George\nSimon Kim\nAli Sartaz Khan\nArpandeep Khatua\nAlisa Levin\nShicheng Liu\nWei Liu\nMinsik Oh\nChenglei Si\nMirac Suzgun\nTristan Thrush\nFang Wu\nQinan Yu\nLogistics\nLectures:\nare on Tuesday/Thursday 4:30 PM - 5:50 PM Pacific Time in\nNVIDIA Auditorium\n. The lectures will also be livestreamed on\nCanvas\nvia Panopto.\nLecture videos for enrolled students:\nare posted on\nCanvas\n(requires login) shortly after\n each lecture ends. Unfortunately, it is not possible to make these videos viewable by non-enrolled students.\nPublicly available lecture videos and versions of the course:\nComplete videos for the CS224N course are\n available (free!) on\nthe CS224N 2024 YouTube\n playlist\n.\n Anyone is welcome to enroll in\nXCS224N: Natural\n Language Processing with Deep Learning\n, the Stanford Artificial Intelligence Professional Program version of\n this course, throughout the year (medium fee, community TAs and certificate). Stanford students enroll normally in\n CS224N and others can also enroll in\nCS224N via Stanford\n online\n(high cost, limited enrollment,\n gives Stanford credit).\n The lecture slides and assignments are updated online each year as the course progresses. We are happy for anyone\n to use these resources, and we are happy to get acknowledgements.\nOffice hours\n: Hybrid format with remote (over Zoom) or in person options. Information\nhere\n.\nContact\n: Students should ask\nall\ncourse-related questions in the Ed forum, where you will also\n find announcements. You will find the course Ed on the course Canvas page or in the header link above.\n For external enquiries, emergencies, or personal matters that you don't wish to put in a private Ed post, you can\n email us at\ncs224n-staff-win2526@cs.stanford.edu\n. Please send all emails to this mailing list - do not email the instructors directly.\nContent\nWhat is this course about?\nNatural language processing (NLP) or computational linguistics is one of the most important technologies of the\n information age.\n Applications of NLP are everywhere because people communicate almost everything in language: web search, advertising,\n emails, customer service, language translation, virtual agents, medical reports, politics, etc.\n In the 2010s, deep learning (or neural network) approaches obtained very high performance across many different NLP\n tasks, using single end-to-end neural models that did not require traditional, task-specific feature engineering. In\n the 2020s amazing further progress was made through the scaling of Large Language Models, such as ChatGPT. In this\n course, students will gain a thorough introduction to both the basics of Deep Learning for NLP and the latest\n cutting-edge research on Large Language Models (LLMs).\n Through lectures, assignments and a final project, students will learn the necessary skills to design, implement, and\n understand their own neural network models, using the\nPytorch\nframework.\n“Take it. CS221 taught me algorithms. CS229 taught me math. CS224N taught me how to write machine learning models.”\n– A CS224N student on Carta\nPrevious offerings\nBelow you can find archived websites and student project reports from previous years.\nDisclaimer: assignments change from year to year; please do not do assignments from previous years!\nCS224N Websites\n:\nWinter 2025\n/\nSpring 2024\n/\nWinter 2024\n/\nWinter 2023\n/\nWinter 2022\n/\nWinter 2021\n/\nWinter 2020\n/\nWinter 2019\n/\nWinter 2018\n/\nWinter 2017\n/\nAutumn 2015\n/\nAutumn 2014\n/\nAutumn 2013\n/\nAutumn 2012\n/\nAutumn 2011\n/\nWinter 2011\n/\nSpring 2010\n/\nSpring 2009\n/\nSpring 2008\n/\nSpring 2007\n/\nSpring 2006\n/\nSpring 2005\n/\nSpring 2004\n/\nSpring 2003\n/\nSpring 2002\n/\nSpring 2000\nCS224N Lecture Videos\n:\nSpring 2024\n/\nWinter 2023\n/\nWinter 2021\n/\nWinter 2019\n/\nWinter 2017\nCS224N Reports\n:\nWinter 2024\n/\nWinter 2023\n/\nWinter 2022\n/\nWinter 2021\n/\nWinter 2020\n/\nWinter 2019\n/\nWinter 2018\n/\nWinter 2017\n/\nAutumn 2015 and earlier\nCS224d Reports\n:\nSpring 2016\n/\nSpring 2015\nPrerequisites\nProficiency in Python\nAll class assignments will be in Python (using\nNumPy\nand\nPyTorch\n). If you need to remind yourself of Python, or you're not very familiar with NumPy, you can come to the Python review session in week 1 (listed in the\nschedule\n). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Java/Javascript), you will probably be fine.\nCollege Calculus, Linear Algebra\n(e.g. MATH 51, CME 100)\nYou should be comfortable taking (multivariable) derivatives and understanding matrix/vector notation and operations.\nBasic Probability and Statistics\n(e.g. CS 109 or equivalent)\nYou should know the basics of probabilities, gaussian distributions, mean, standard deviation, etc.\nFoundations of Machine Learning\n(e.g. CS221, CS229, CS230, or CS124)\nWe will be formulating cost functions, taking derivatives and performing optimization with gradient descent.\n If you already have basic machine learning and/or deep learning knowledge, the course will be easier; however it is possible to take CS224N without it. There are many introductions to ML, in webpage, book, and video form. One approachable introduction is Hal Daumé’s in-progress\nA Course in Machine Learning\n. Reading the first 5 chapters of that book would be good background. Knowing the first 7 chapters would be even better!\nReference Texts\nThe following texts are useful, but none are required. All of them can be read free online.\nDan Jurafsky and James H. Martin.\nSpeech and Language Processing (2024 pre-release)\nJacob Eisenstein.\nNatural Language Processing\nYoav Goldberg.\nA Primer on Neural Network Models for Natural Language Processing\nIan Goodfellow, Yoshua Bengio, and Aaron Courville.\nDeep Learning\nDelip Rao and Brian McMahan.\nNatural Language Processing with PyTorch\n(requires Stanford login).\nLewis Tunstall, Leandro von Werra, and Thomas Wolf.\nNatural Language Processing with Transformers\nIf you have no background in neural networks but would like to take the course anyway, you might well find one of these books helpful to give you more background:\nMichael A. Nielsen.\nNeural Networks and Deep Learning\nEugene Charniak.\nIntroduction to Deep Learning\nCoursework\nDisclaimer: Coursework is tentative and subject to change!\nAssignments (48%)\nThere are four weekly assignments, which will improve both your theoretical understanding and your practical skills. All assignments contain both written questions and programming parts. In office hours, TAs may look at students’ code for assignments 1 and 2, but not for assignments 3 and 4.\nCredit\n:\nAssignment 1 (6%): Introduction to word vectors\nAssignment 2 (14%): Neural network foundations, calculating tensor derivatives, dependency parsing\nAssignment 3 (14%): Self-attention and Transformers\nAssignment 4 (14%): Large language model benchmarking and evaluation\nDeadlines\n: All assignments are due on either a Tuesday or a Thursday\nbefore class\n(i.e. before 4:30pm). All deadlines are listed in the\nschedule\n.\nSubmission\n: Assignments are submitted via\nGradescope\n. You will be able to access the course Gradescope page on Canvas. If you need to sign up for a Gradescope account, please use your\n@stanford.edu\nemail address. Further instructions are given in each assignment handout.\nDo not email us your assignments\n.\nLate start\n: If the result gives you a higher grade, we will not use your assignment 1 score, and we will give you an assignment grade based on counting each of assignments 2–4 at 16%.\nCollaboration\n:\n Study groups are allowed, but students must understand and complete their own assignments, and hand in one assignment per student.\n If you worked in a group, please put the names of the members of your study group at the top of your assignment.\n Please ask if you have any questions about the collaboration policy.\nHonor Code\n:\n We expect students to not look at solutions or implementations online. Like all other classes at Stanford, we take the student\nHonor Code\nseriously. We sometimes use automated methods to detect overly similar assignment solutions.\nFinal Project (49%)\nThe Final Project offers you the chance to apply your newly acquired skills towards an in-depth application.\n Students have two options: the\nDefault Final Project\n(in which students tackle a predefined task, namely implementing a minimalist version of GPT-2) or a\nCustom Final Project\n(in which students choose their own project involving human language and deep learning). Examples of both can be seen on the\nSpring 2024 website\n.\nNote: TAs may not look at students' code for either the default or custom final projects. The Spring 2024 Default Final Project was based on BERT and has now been replaced with GPT-2.\nImportant information\nCredit\n: For both default and custom projects, credit for the final project is broken down as follows:\nProject proposal (8%)\nProject milestone (6%)\nProject poster (3%)\nProject report (32%)\nDeadlines\n: The project proposal, milestone and report are all due at 4:30pm. All deadlines are listed in the\nschedule\n.\nDefault Final Project\n: In this project, students implement parts of the GPT-2 architecture and use it to tackle 3 downstream tasks.\n Similar to previous years, the code is in PyTorch.\nProject advice\n[\nlecture slides\n] [\ncustom project tips\n]: The\nPractical Tips for Final Projects\nlecture provides guidance for choosing and planning your project.\n To get project advice from staff members, first look at each staff member's areas of expertise on the\noffice hours page\n. This should help you find a staff member who is knowledgable about your project area.\nEthics-related questions\n: For guidance on projects dealing with ethical questions, or ethical questions that arise during your project, please contact Wanheng Hu (\nwanhenghu@stanford.edu\n) or Justin Shin (\njustinjs@stanford.edu\n).\nPracticalities\nTeam size\n: Students may do final projects solo, or in teams of up to 3 people. We strongly recommend you do the final project in a team. Larger teams are expected to do correspondingly larger projects, and you should only form a 3-person team if you are planning to do an ambitious project where every team member will have a significant contribution.\nContribution\n: In the final report we ask for a statement of what each team member contributed to the project. Team members will typically get the same grade, but we may differentiate in extreme cases of unequal contribution. You can contact us in confidence in the event of unequal contribution.\nExternal collaborators\n: You can work on a project that has external (non CS224N student) collaborators, but you must make it clear in your final report which parts of the project were your work.\nSharing projects\n: You can share a single project between CS224N and another class, but we expect the project to be accordingly bigger, and you must declare that you are sharing the project in your project proposal.\nMentors\n: Every custom project team has a mentor, who gives feedback and advice during the project. Default project teams do not have mentors. A project may have an external (i.e., not course staff) mentor; otherwise, we will assign a CS224N staff mentor to custom project teams after project proposals.\nComputing resources\n: All teams will receive compute credits thanks to kind donations by Google, Kimi, Modal, and Qwen!\nUsing external resources\n: The following guidelines apply to all projects (though the default project has some more specific rules, details provided in the\nHonor Code\nsection of the\nhandout\n):\nYou can use any deep learning framework you like (PyTorch, TensorFlow, etc.)\nMore generally, you may use any existing code, libraries, etc. and consult any papers, books, online references, etc. for your project. However, you must cite your sources in your writeup and clearly indicate which parts of the project are your contribution and which parts were implemented by others.\nUnder no circumstances may you look at another CS224N group's code, or incorporate their code into your project.\nParticipation (3%)\nWe appreciate everyone being actively involved in the class! There are several ways of earning participation credit, which is capped at 3%:\nAttending guest speakers' lectures\n:\nIn the second half of the class, we have four invited speakers.\n Our guest speakers make a significant effort to come lecture for us, so\n (both to show our appreciation and to continue attracting interesting speakers)\n we do not want them lecturing to a largely empty room.\n As such, we encourage students to attend these virtual lectures live, and participate in Q&A.\nAll students get 0.375% per speaker (1.5% total) for either attending the guest lecture in person, or by writing a reaction paragraph if you watched the talk remotely; details will be provided.\n Students do not need to attend lecture live to write these reaction paragraphs; they may watch asynchronously.\nCompleting feedback surveys\n: We will send out two feedback surveys (mid-quarter and end-of-quarter) to help us understand how the course is going, and how we can improve. Each of the two surveys are worth 0.5%.\nEd participation\n: The top ~20 contributors to Ed will get 3%; others will get credit in proportion to the participation of the ~20th person.\nKarma point\n: Any other act that improves the class, like helping out another student in office hours or writing a useful guide for students on some topic, which a CS224N TA or instructor notices and deems worthy: 1%\nLate Days\nEach student has 6 late days to use. A late day extends the deadline 24 hours. You can use up to 3 late days per assignment (including all four assignments, project proposal, project milestone, and project final report).\nOnce you have used all 6 late days, the penalty is 1% off the final course grade for each additional late day.\nProject proposal and milestone (late days are NOT shared):\nLate days are applied individually and are not pooled across the team. If a student does not have enough late days remaining, that student receives a 1% deduction to their total course grade for each late day they are short — this penalty applies only to that student.\nFinal project report (late days CAN be shared):\nLate days may be pooled across team members. For example, in a team of three students, the team's total available late days is the sum of each member's remaining late days, divided by three to determine how many days late the team can submit.\nAt the top of your final report, you must state how many late days your team is pooling and which team members have late days remaining.\nRegrade Requests\nIf you feel you deserved a better grade on an assignment, you may submit a regrade request on Gradescope within 3 days after the grades are released.\n Your request should briefly summarize why you feel the original grade was unfair.\n Your TA will reevaluate your assignment as soon as possible, and then issue a decision.\n If you are still not happy, you can ask for your assignment to be regraded by an instructor.\nDisclaimer: the course staff reserve the right to regrade your entire assignment in addition to the specific questions you request. Submit regrade requests at your own risk.\nCredit/No credit enrollment\nIf you take the class credit/no credit then you are graded in the same way as those registered for a letter grade. The only difference is that, providing you reach a C- standard in your work, it will simply be graded as CR.\nAll students welcome\nWe are committed to doing what we can to work for equity and to create an inclusive learning environment that actively values the diversity of backgrounds, identities, and experiences of everyone in CS224N. We also know that we will sometimes make missteps. If you notice some way that we could do better, we hope that you will let someone in the course staff know about it.\nWell-Being and Mental Health\nIf you are experiencing personal, academic, or relationship problems and would like to talk to someone with training and experience, reach out to the\nCounseling and Psychological Services (CAPS)\non campus. CAPS is the university’s counseling center dedicated to student mental health and wellbeing. Phone assessment appointments can be made at CAPS by calling 650-723-3785, or by accessing the VadenPatient portal through the Vaden website.\nAuditing the course\nIn general we are happy to have auditors if they are a member of the Stanford community (registered student, official visitor, staff, or faculty). If you are interested, email us at\ncs224n-staff-win2526@cs.stanford.edu\n. If you want to actually master the material of the class, we very strongly recommend that auditors do all the assignments. However, due to high enrollment, we cannot grade the work of any students who are not officially enrolled in the class.\nStudents with Documented Disabilities\nWe assume that all of us learn in different ways, and that the organization of the course must accommodate each student differently. We are committed to ensuring the full participation of all enrolled students in this class.\n If you need an academic accommodation based on a disability, you should initiate the request with the\nOffice of Accessible Education (OAE)\n.\n The OAE will evaluate the request, recommend accommodations, and prepare a letter for faculty. Students should contact the OAE as soon as possible and at any rate in advance of assignment deadlines, since timely notice is needed to coordinate accommodations. Students should also send your accommodation letter to either the staff mailing list (\ncs224n-staff-win2526@cs.stanford.edu\n) or make a private post on Ed, as soon as possible.\nOAE accommodations for group projects:\nOAE accommodations will not be extended to collaborative assignments.\nAI Tools Policy\nStudents are required to independently submit their solutions for CS224N homework assignments. Collaboration with generative AI tools such as Co-Pilot and ChatGPT is allowed, treating them as collaborators in the problem-solving process. However, the direct solicitation of answers or copying solutions, whether from peers or external sources, is strictly prohibited.\nEmploying AI tools to substantially complete assignments or exams will be considered a violation of the Honor Code.\nFor additional details, please refer to the Generative AI Policy Guidance\nhere\n.\nSexual violence\nAcademic accommodations are available for students who have experienced or are recovering from sexual violence. If you would like to talk to a confidential resource, you can schedule a meeting with the Confidential Support Team or call their 24/7 hotline at: 650-725-9955. Counseling and Psychological Services also offers confidential counseling services. Non-confidential resources include the Title IX Office, for investigation and accommodations, and the SARA Office, for healing programs. Students can also speak directly with the teaching staff to arrange accommodations. Note that university employees – including professors and TAs – are required to report what they know about incidents of sexual or relationship violence, stalking and sexual harassment to the Title IX Office. Students can learn more at\nhttps://vaden.stanford.edu/sexual-assault\n.\nSchedule\nUpdated lecture\nslides\nwill be posted here shortly before each lecture. Lecture\nnotes\nwill be uploaded a few days after most lectures. The notes (which cover approximately the first half of the course content) give supplementary detail beyond the lectures.\nDisclaimer: Schedule is tentative and subject to change!\nDisclaimer: Assignments change; please do not do old assignments. We will give no points for doing last year's assignments.\nDate\nDescription\nCourse Materials\nEvents\nDeadlines\nWeek 1\nTue Jan 6\nHistory of NLP\n[\nintro slides\n]\n [\nhistory slides\n]\nSuggested Readings:\nHuman Language Understanding & Reasoning\nAssignment 1\nout\n[\ncode\n]\nThu Jan 8\nWord Vectors\n[\nslides\n]\n [\nnotes 1\n]\n [\nnotes 2\n]\nSuggested Readings:\nEfficient Estimation of Word Representations in Vector Space\n(original word2vec paper)\nDistributed Representations of Words and Phrases and their Compositionality\n(negative sampling paper)\nGloVe: Global Vectors for Word Representation\n(original GloVe paper)\nImproving Distributional Similarity with Lessons Learned from Word Embeddings\nEvaluation methods for unsupervised word embeddings\nAdditional Readings:\nA Latent Variable Model Approach to PMI-based Word Embeddings\nLinear Algebraic Structure of Word Senses, with Applications to Polysemy\nOn the Dimensionality of Word Embedding\nFri Jan 9\nPython Review Session\n[\nslides\n]\n [\ncolab\n]\nTime 1:30pm-2:50pm\nLocation NVIDIA Auditorium\nWeek 2\nTue Jan 13\nBackpropagation and Neural Network Basics\n[\nslides\n]\n [\nnotes\n]\nSuggested Readings:\nmatrix calculus notes\nReview of differential calculus\nCS231n notes on network architectures\nCS231n notes on backprop\nDerivatives, Backpropagation, and Vectorization\nLearning Representations by Backpropagating Errors\n(seminal Rumelhart et al. backpropagation paper)\nAdditional Readings:\nYes you should understand backprop\nNatural Language Processing (Almost) from Scratch\nAssignment 2\nout\n[\ncode\n]\n[\nhandout\n]\n[\nlatex template\n]\nAssignment 1\ndue\nThu Jan 15\nLanguage Models and RNNs\n[\nslides\n]\n [\nnotes\n]\nSuggested Readings:\nLearning long-term dependencies with gradient descent is difficult\n(one of the original vanishing gradient papers)\nOn the difficulty of training Recurrent Neural Networks\n(proof of vanishing gradient problem)\nVanishing Gradients Jupyter Notebook\n(demo for feedforward networks)\nAttention Is All You Need\nFri Jan 16\nPyTorch Tutorial Session\n[\ncolab\n]\nTime 1:30pm-2:50pm\nLocation NVIDIA Auditorium\nWeek 3\nTue Jan 20\nTransformers\n[\nslides\n]\n [\nnotes\n]\nSuggested Readings:\nAttention Is All You Need\nThe Illustrated Transformer\nTransformer (Google AI blog post)\nLayer Normalization\nImage Transformer\nMusic Transformer: Generating music with long-term structure\nJurafsky and Martin Chapter 9 (The Transformer)\nThu Jan 22\nFinal Projects: Custom and Default; Practical Tips\n[\nslides\n]\nSuggested Readings:\nPractical Methodology\n(\nDeep Learning\nbook chapter)\nAssignment 3\nout\n[\ncode\n]\n[\nhandout\n]\n[\nlatex template\n]\nAssignment 2\ndue\nWeek 4\nTue Jan 27\nPretraining (Scaling, Systems, Data)\n[\nslides\n]\nSuggested Readings:\nBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding\nContextual Word Representations: A Contextual Introduction\nThe Illustrated BERT, ELMo, and co.\nJurafsky and Martin Chapter 10 (Masked Language Models)\nThe Llama 3 Herd of Models\nThu Jan 29\nPost-training (RLHF, SFT, DPO) \n [\nslides\n]\nSuggested Readings:\nAligning language models to follow instructions\nScaling Instruction-Finetuned Language Models\nAlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback\nHow Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources\nDirect Preference Optimization: Your Language Model is Secretly a Reward Model\nProject Proposal\nout\n[\nhandout\n]\nDefault Final Project\nout\n[\nhandout\n]\nWeek 5\nTue Feb 3\nEfficient Adaptation (Prompting + PEFT)\n[\nslides\n]\nSuggested Readings:\nLanguage Models are Few-Shot Learners\nChain-of-Thought Prompting Elicits Reasoning in Large Language Models\nThe Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks\nLoRA: Low-Rank Adaptation of Large Language Models\nParameter-Efficient Transfer Learning for NLP\nThu Feb 5\nAgents, Tool Use, and RAG\n[\nslides\n]\nSuggested Readings:\nReAct: Synergizing Reasoning and Acting in Language Models\nLanguage Agents: Foundations, Prospects, and Risks\nRetrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\nToolformer: Language Models Can Teach Themselves to Use Tools\nAssignment 4\nout\n[\ncode\n]\n[\nhandout\n]\n[\nlatex template\n]\nAssignment 3\ndue\nFri Feb 6\nHugging Face Transformers Tutorial Session\n[\nslides\n]\n [\ncolab\n]\nTime 1:30pm-2:50pm\nLocation NVIDIA Auditorium\nWeek 6\nTue Feb 10\nBenchmarking and Evaluation\n [\nslides\n]\nSuggested Readings:\nChallenges and Opportunities in NLP Benchmarking\nMeasuring Massive Multitask Language Understanding\nHolistic Evaluation of Language Models\nAlpacaEval\nProject Proposal & Mentor Form\ndue\nThu Feb 12\nReasoning 1\n[\nslides\n]\nSuggested Readings:\nChain-of-Thought Prompting Elicits Reasoning in Large Language Models\nSelf-Consistency Improves Chain of Thought Reasoning in Language Models\nDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning\nDAPO: An Open-Source LLM Reinforcement Learning System at Scale\nWeek 7\nTue Feb 17\nReasoning 2\n[\nslides\n]\nSuggested Readings:\nLet's Verify Step by Step\nFast Inference from Transformers via Speculative Decoding\nScaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters\nRoFormer: Enhanced Transformer with Rotary Position Embedding\nProject Milestone\nout\n[\nhandout\n]\nFinal Project Proposals\nreturned\nThu Feb 19\nGuest Lecture: Tokenization and Multilinguality (by\nJulie Kallini\n)\n [\nslides\n]\nSuggested readings:\nJurafsky & Martin Chapter 2\nNeural Machine Translation of Rare Words with Subword Units\nUnsupervised Cross-lingual Representation Learning at Scale\nDo All Languages Cost the Same? Tokenization in the Era of Commercial Language Models\nAssignment 4\ndue\nWeek 8\nTue Feb 24\nGuest Lecture: Interpretability (by\nBeen Kim\n)\nSuggested readings:\nBecause we have LLMs, we Can and Should Pursue Agentic Interpretability\nThe Pareto Frontier of Human-Centered AI\nBridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero\nWe Can't Understand AI Using our Existing Vocabulary\nNeologism Learning for Controllability and Self-Verbalization\nFinal Project Report Instructions\nout\n[\nInstructions\n]\nThu Feb 26\nSocial and Broader Impacts of NLP (Risks)\n[\nslides\n]\nFinal Project Milestone\ndue\nFri Feb 27\nCourse Withdrawal Deadline\nWeek 9\nTue Mar 3\nGuest Lecture: Multimodality (by\nLuke Zettlemoyer\n)\nSuggested readings:\nVisual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models\nChameleon: Mixed-Modal Early-Fusion Foundation Models\nTransfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model\nMixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models\nOptional readings:\nScaling Laws for Generative Mixed-Modal Language Models\nScaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning\nRetrieval Augmented Multimodal Language Modeling\nLMFusion: Adapting Pretrained Language Models for Multimodal Generation\nOneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows\nMultimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models\nReconstruction Alignment Improves Unified Multimodal Models\nFinal Project Milestones\nreturned\nThu Mar 5\nGuest Lecture: Tinker and LoRA Without Regret (by\nJohn Schulman\n)\nWeek 10\nTue Mar 10\nOpen Questions in NLP 2026\n [\nslides\n]\nThu Mar 12\nNo Lecture\nFinal project\ndue\nMon Mar 16\nFinal Project Poster Session\nTime 12:15pm-3:15pm\nLocation AOERC\nALL On-campus students must attend in person!\n[\nPrinting guide\n]\nSponsors\nWe are grateful to our sponsors for their generous support of CS224N.", "metadata": { "title": "Stanford CS 224N | Natural Language Processing with Deep Learning", "description": null, "keywords": null, "author": null }, "paywall": { "listed_paid": false, "detected": false, "marker": "", "public_only": false, "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙" }, "crawl": { "success": true, "status_code": 200, "error": "" }, "code_blocks": [], "images": [ { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images/stanford-nlp-logo-new.jpg", "bytes": 25713, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-399e1a660c843ac34f1b.jpg", "src": "https://web.stanford.edu/class/cs224n/images/stanford-nlp-logo-new.jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images/stanfordlogo.jpg", "bytes": 6856, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-5747545207eee3f3cb9b.jpg", "src": "https://web.stanford.edu/class/cs224n/images/stanfordlogo.jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Diyi Yang.jpg", "bytes": 165094, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-eb7cd3a5de9b617041ed.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Diyi Yang.jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Yejin Choi.jpg", "bytes": 1401577, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-7cbfd5918890deb65e53.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Yejin Choi.jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/John Cho (Course Manager).jpg", "bytes": 27494, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-b7d4bd0b135e0a72712a.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/John Cho (Course Manager).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Swati Dube Batra (Course Manager Advisor).jpg", "bytes": 279678, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-4153915107deb9c5b251.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Swati Dube Batra (Course Manager Advisor).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Julie Kallini (Head TA).jpg", "bytes": 2314272, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-221cb8268cfa46f08086.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Julie Kallini (Head TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Ahmed Ahmed (TA).jpg", "bytes": 120974, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-b2899132223205042cc9.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Ahmed Ahmed (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/David Anugraha (TA).jpg", "bytes": 79920, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-be0aaebf09fab7e3e384.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/David Anugraha (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Luke Bailey (TA).jpg", "bytes": 594962, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-7a3b1d758835eeec22cd.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Luke Bailey (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Sarah Chen (TA).png", "bytes": 314311, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-dedfef4bc7e4b3abe24b.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/Sarah Chen (TA).png", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Caroline Choi (TA).jpg", "bytes": 707328, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-d74b956c7bb072fd488b.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Caroline Choi (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Advit Deepak (TA).jpg", "bytes": 197197, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-b45991547f1a67cee8ba.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Advit Deepak (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Nevin George (TA).jpg", "bytes": 24588, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-6e293e975d671f4f392c.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Nevin George (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Simon Kim (TA).jpg", "bytes": 28760, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-078bd7082efe352795a4.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Simon Kim (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Ali Sartaz Khan (TA).png", "bytes": 364757, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-a6dd82b66ff2b1c8d0ea.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/Ali Sartaz Khan (TA).png", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Arpandeep Khatua (TA).jpg", "bytes": 209224, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-73012e450a301026b031.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Arpandeep Khatua (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Alisa Levin (TA).jpg", "bytes": 349397, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-df2063682bd2bbb63eb1.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Alisa Levin (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Shicheng Liu (TA).jpg", "bytes": 1589101, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-c25e5e463c3cf74bb0d1.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Shicheng Liu (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Wei Liu (TA).jpg", "bytes": 564064, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-a61d2e23440e4cecc7da.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Wei Liu (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Minsik Oh (TA).jpg", "bytes": 1354575, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-97bf033775cee09a4f04.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Minsik Oh (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Chenglei Si (TA).jpg", "bytes": 967543, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-29875d1d66496a2bae3b.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Chenglei Si (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Mirac Suzgun (TA).jpg", "bytes": 1809818, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-413b759c9d075ca4e977.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Mirac Suzgun (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Tristan Thrush (TA).jpg", "bytes": 127564, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-2efcab2791652e921436.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Tristan Thrush (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Fang Wu (TA).jpg", "bytes": 4311936, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-920a348c799ccb020199.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Fang Wu (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/Qinan Yu (TA).jpg", "bytes": 1538458, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-49506e56b2dfcc700942.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/Qinan Yu (TA).jpg", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_microsoft.png", "bytes": 80702, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-8e2814f6287f0e5a472f.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_microsoft.png", "alt": "Microsoft", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_atlassian.png", "bytes": 17153, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-08f4638d3d375ad14bb0.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_atlassian.png", "alt": "Atlassian", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_janestreet.png", "bytes": 135081, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-d82d6ac6c6e508c7a6d8.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_janestreet.png", "alt": "Jane Street", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_neocognition.png", "bytes": 3277, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-46f093ce6aaf8d5e80e1.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_neocognition.png", "alt": "NeoCognition", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_pinetwork.jpg", "bytes": 30878, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-6a0fe595874a8438a05b.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_pinetwork.jpg", "alt": "Pi Network", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_tola.png", "bytes": 37964, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-1b6f8b0474c2956b4325.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_tola.png", "alt": "Tola Capital", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_modal.jpg", "bytes": 41471, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-28cfd7b65e3628d08a9f.jpg", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_modal.jpg", "alt": "Modal", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_gcp.png", "bytes": 51700, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-3f80457f78d5f90f88d9.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_gcp.png", "alt": "Google Cloud Platform", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_qwen.png", "bytes": 10655, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-c230cb7ea9cce65635cc.png", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_qwen.png", "alt": "Qwen", "downloaded": true }, { "status": "ok", "url": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_kimi.svg", "bytes": 1087477, "reused": false, "local_path": "attachments/aa5b9c1e53d2/images/body-b6f09ca568f2fc595eb5.svg", "src": "https://web.stanford.edu/class/cs224n/images_w26/logos/sponsor_kimi.svg", "alt": "Kimi", "downloaded": true } ], "audio": [], "videos": [ { "url": "https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D", "src": "https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D", "status": "partial", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=DzpHeXVSC5I", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] DzpHeXVSC5I: Video unavailable\n", "retried_at": "2026-10-20T17:43:02Z" }, { "url": "https://www.youtube.com/watch?v=nBor4jfWetQ", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] nBor4jfWetQ: Video unavailable\n", "retried_at": "2026-10-20T17:43:07Z" }, { "url": "https://www.youtube.com/watch?v=HnliVHU2g9U", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] HnliVHU2g9U: Video unavailable\n", "retried_at": "2026-10-20T17:43:06Z" }, { "url": "https://www.youtube.com/watch?v=KVKvde-_MYc", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] KVKvde-_MYc: Video unavailable\n", "retried_at": "2026-10-20T17:43:09Z" }, { "url": "https://www.youtube.com/watch?v=fyc0Jzr74y4", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] fyc0Jzr74y4: Video unavailable\n", "retried_at": "2026-10-20T17:43:12Z" }, { "url": "https://www.youtube.com/watch?v=Ba6Fn1-Jsfw", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] Ba6Fn1-Jsfw: Video unavailable\n", "retried_at": "2026-10-20T17:43:12Z" }, { "url": "https://www.youtube.com/watch?v=J7ruSOIzhrE", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] J7ruSOIzhrE: Video unavailable\n", "retried_at": "2026-10-20T17:43:12Z" }, { "url": "https://www.youtube.com/watch?v=LWMzyfvuehA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] LWMzyfvuehA: Video unavailable\n", "retried_at": "2026-10-20T17:43:16Z" }, { "url": "https://www.youtube.com/watch?v=DGfCRXuNA2w", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] DGfCRXuNA2w: Video unavailable\n", "retried_at": "2026-10-20T17:43:15Z" }, { "url": "https://www.youtube.com/watch?v=N9L32bFieEY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] N9L32bFieEY: Video unavailable\n", "retried_at": "2026-10-20T17:43:16Z" }, { "url": "https://www.youtube.com/watch?v=35X6zlhoCy4", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 35X6zlhoCy4: Video unavailable\n", "retried_at": "2026-10-20T17:43:18Z" }, { "url": "https://www.youtube.com/watch?v=TO0CqzqiArM", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] TO0CqzqiArM: Video unavailable\n", "retried_at": "2026-10-20T17:43:21Z" }, { "url": "https://www.youtube.com/watch?v=UVX7SYGCKkA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] UVX7SYGCKkA: Video unavailable\n", "retried_at": "2026-10-20T17:43:19Z" }, { "url": "https://www.youtube.com/watch?v=tfVgHsKpRC8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] tfVgHsKpRC8: Video unavailable\n", "retried_at": "2026-10-20T17:43:22Z" }, { "url": "https://www.youtube.com/watch?v=I0tj4Y7xaOQ", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] I0tj4Y7xaOQ: Video unavailable\n", "retried_at": "2026-10-20T17:43:23Z" }, { "url": "https://www.youtube.com/watch?v=dnF463_Ar9I", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] dnF463_Ar9I: Video unavailable\n", "retried_at": "2026-10-20T17:43:24Z" }, { "url": "https://www.youtube.com/watch?v=S8d-7v3f5MQ", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] S8d-7v3f5MQ: Video unavailable\n", "retried_at": "2026-10-20T17:43:25Z" }, { "url": "https://www.youtube.com/watch?v=NxH0Y78xcF4", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] NxH0Y78xcF4: Video unavailable\n", "retried_at": "2026-10-20T17:43:26Z" }, { "url": "https://www.youtube.com/watch?v=5vfIT5LOkR0", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 5vfIT5LOkR0: Video unavailable\n", "retried_at": "2026-10-20T17:43:29Z" }, { "url": "https://www.youtube.com/watch?v=cd3pRpEtjLs", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] cd3pRpEtjLs: Video unavailable\n", "retried_at": "2026-10-20T17:43:28Z" }, { "url": "https://www.youtube.com/watch?v=8j4wpU98Q74", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 8j4wpU98Q74: Video unavailable\n", "retried_at": "2026-10-20T17:44:25Z" }, { "url": "https://www.youtube.com/watch?v=Uv0AIRr3ptg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] Uv0AIRr3ptg: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=b80by3Xk_A8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] b80by3Xk_A8: Video unavailable\n", "retried_at": "2026-10-20T17:44:25Z" } ], "retried_at": "2026-10-18T17:12:08Z" }, { "url": "https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4", "src": "https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4", "status": "partial", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=rmVRLeJRkl4", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/rmVRLeJRkl4.mp4", "bytes": 244189980, "valid": true, "height": 1080, "width": 1920, "duration": "5066.981000", "reused": true, "retried_at": "2026-10-18T18:18:13Z" }, { "url": "https://www.youtube.com/watch?v=gqaHkPEZAew", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] gqaHkPEZAew: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=X0Jw4kgaFlg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] X0Jw4kgaFlg: Video unavailable\n", "retried_at": "2026-10-20T17:44:28Z" }, { "url": "https://www.youtube.com/watch?v=PSGIodTN3KE", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] PSGIodTN3KE: Video unavailable\n", "retried_at": "2026-10-20T17:44:30Z" }, { "url": "https://www.youtube.com/watch?v=PLryWeHPcBs", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] PLryWeHPcBs: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=0LixFSa7yts", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 0LixFSa7yts: Video unavailable\n", "retried_at": "2026-10-20T17:44:28Z" }, { "url": "https://www.youtube.com/watch?v=wzfWHP6SXxY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] wzfWHP6SXxY: Video unavailable\n", "retried_at": "2026-10-20T17:44:29Z" }, { "url": "https://www.youtube.com/watch?v=LWMzyfvuehA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] LWMzyfvuehA: Video unavailable\n", "retried_at": "2026-10-20T17:43:16Z" }, { "url": "https://www.youtube.com/watch?v=DGfCRXuNA2w", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] DGfCRXuNA2w: Video unavailable\n", "retried_at": "2026-10-20T17:43:15Z" }, { "url": "https://www.youtube.com/watch?v=SXpJ9EmG3s4", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] SXpJ9EmG3s4: Video unavailable\n", "retried_at": "2026-10-20T17:44:30Z" }, { "url": "https://www.youtube.com/watch?v=N9L32bFieEY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] N9L32bFieEY: Video unavailable\n", "retried_at": "2026-10-20T17:43:16Z" }, { "url": "https://www.youtube.com/watch?v=NcqfHa0_YmU", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-NcqfHa0_YmU.mp4", "bytes": 359194597, "valid": true, "height": 1080, "width": 1920, "duration": "6712.241000", "reused": true, "reused_from": "open-courses-0923/01-CS224N-Natural-Language-Processing-with/videos/repair-NcqfHa0_YmU.mp4", "retried_at": "2026-10-18T18:18:21Z" }, { "url": "https://www.youtube.com/watch?v=FFRnDRcbQQU", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] FFRnDRcbQQU: Video unavailable\n", "retried_at": "2026-10-20T17:44:31Z" }, { "url": "https://www.youtube.com/watch?v=NvIWF82Fw4E", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/NvIWF82Fw4E.mp4", "bytes": 241222067, "valid": true, "height": 1080, "width": 1920, "duration": "4771.781000", "reused": true, "retried_at": "2026-10-18T18:18:22Z" }, { "url": "https://www.youtube.com/watch?v=y68RJVfGoto", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] y68RJVfGoto: Video unavailable\n", "retried_at": "2026-10-20T17:44:31Z" }, { "url": "https://www.youtube.com/watch?v=JlK46EzImM8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] JlK46EzImM8: Video unavailable\n", "retried_at": "2026-10-20T17:44:34Z" }, { "url": "https://www.youtube.com/watch?v=f_qmSSBWV_E", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] f_qmSSBWV_E: Video unavailable\n", "retried_at": "2026-10-20T17:44:36Z" }, { "url": "https://www.youtube.com/watch?v=2t7Q9WVUaf8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 2t7Q9WVUaf8: Video unavailable\n", "retried_at": "2026-10-20T17:44:34Z" }, { "url": "https://www.youtube.com/watch?v=8j4wpU98Q74", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 8j4wpU98Q74: Video unavailable\n", "retried_at": "2026-10-20T17:44:25Z" }, { "url": "https://www.youtube.com/watch?v=Uv0AIRr3ptg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] Uv0AIRr3ptg: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=b80by3Xk_A8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] b80by3Xk_A8: Video unavailable\n", "retried_at": "2026-10-20T17:44:25Z" }, { "url": "https://www.youtube.com/watch?v=5vfIT5LOkR0", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 5vfIT5LOkR0: Video unavailable\n", "retried_at": "2026-10-20T17:43:29Z" }, { "url": "https://www.youtube.com/watch?v=cd3pRpEtjLs", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] cd3pRpEtjLs: Video unavailable\n", "retried_at": "2026-10-20T17:43:28Z" } ], "retried_at": "2026-10-18T17:12:08Z" }, { "url": "https://www.youtube.com/playlist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ", "src": "https://www.youtube.com/playlist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ", "status": "partial", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=rmVRLeJRkl4", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/rmVRLeJRkl4.mp4", "bytes": 244189980, "valid": true, "height": 1080, "width": 1920, "duration": "5066.981000", "reused": true, "retried_at": "2026-10-18T18:18:13Z" }, { "url": "https://www.youtube.com/watch?v=gqaHkPEZAew", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] gqaHkPEZAew: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=X0Jw4kgaFlg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] X0Jw4kgaFlg: Video unavailable\n", "retried_at": "2026-10-20T17:44:28Z" }, { "url": "https://www.youtube.com/watch?v=PSGIodTN3KE", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] PSGIodTN3KE: Video unavailable\n", "retried_at": "2026-10-20T17:44:30Z" }, { "url": "https://www.youtube.com/watch?v=PLryWeHPcBs", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] PLryWeHPcBs: Video unavailable\n", "retried_at": "2026-10-20T17:44:26Z" }, { "url": "https://www.youtube.com/watch?v=0LixFSa7yts", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 0LixFSa7yts: Video unavailable\n", "retried_at": "2026-10-20T17:44:28Z" }, { "url": "https://www.youtube.com/watch?v=wzfWHP6SXxY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] wzfWHP6SXxY: Video unavailable\n", "retried_at": "2026-10-20T17:44:29Z" }, { "url": "https://www.youtube.com/watch?v=gKD7jPAdbpE", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] gKD7jPAdbpE: Video unavailable\n", "retried_at": "2026-10-20T17:44:35Z" }, { "url": "https://www.youtube.com/watch?v=ptuGllU5SQQ", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] ptuGllU5SQQ: Video unavailable\n", "retried_at": "2026-10-20T17:44:39Z" }, { "url": "https://www.youtube.com/watch?v=j9AcEI98C0o", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] j9AcEI98C0o: Video unavailable\n", "retried_at": "2026-10-20T17:44:37Z" }, { "url": "https://www.youtube.com/watch?v=NcqfHa0_YmU", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-NcqfHa0_YmU.mp4", "bytes": 359194597, "valid": true, "height": 1080, "width": 1920, "duration": "6712.241000", "reused": true, "reused_from": "open-courses-0923/01-CS224N-Natural-Language-Processing-with/videos/repair-NcqfHa0_YmU.mp4", "retried_at": "2026-10-18T18:18:21Z" }, { "url": "https://www.youtube.com/watch?v=1uMo8olr5ng", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 1uMo8olr5ng: Video unavailable\n", "retried_at": "2026-10-20T17:44:37Z" }, { "url": "https://www.youtube.com/watch?v=FFRnDRcbQQU", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] FFRnDRcbQQU: Video unavailable\n", "retried_at": "2026-10-20T17:44:31Z" }, { "url": "https://www.youtube.com/watch?v=iHWkLvoSpTg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] iHWkLvoSpTg: Video unavailable\n", "retried_at": "2026-10-20T17:44:40Z" }, { "url": "https://www.youtube.com/watch?v=y68RJVfGoto", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] y68RJVfGoto: Video unavailable\n", "retried_at": "2026-10-20T17:44:31Z" }, { "url": "https://www.youtube.com/watch?v=-Ldg4qFL6bU", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] -Ldg4qFL6bU: Video unavailable\n", "retried_at": "2026-10-20T17:44:39Z" }, { "url": "https://www.youtube.com/watch?v=f_qmSSBWV_E", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] f_qmSSBWV_E: Video unavailable\n", "retried_at": "2026-10-20T17:44:36Z" }, { "url": "https://www.youtube.com/watch?v=2t7Q9WVUaf8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 2t7Q9WVUaf8: Video unavailable\n", "retried_at": "2026-10-20T17:44:34Z" }, { "url": "https://www.youtube.com/watch?v=mp95Z5yM92c", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] mp95Z5yM92c: Video unavailable\n", "retried_at": "2026-10-20T17:44:41Z" }, { "url": "https://www.youtube.com/watch?v=knTc-NQSjKA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] knTc-NQSjKA: Video unavailable\n", "retried_at": "2026-10-20T17:44:42Z" }, { "url": "https://www.youtube.com/watch?v=iXjtJmUQBZk", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] iXjtJmUQBZk: Video unavailable\n", "retried_at": "2026-10-20T17:44:42Z" }, { "url": "https://www.youtube.com/watch?v=4ynrGLIuPv4", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 4ynrGLIuPv4: Video unavailable\n", "retried_at": "2026-10-20T17:44:42Z" }, { "url": "https://www.youtube.com/watch?v=UFem7xa3Q2Q", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] UFem7xa3Q2Q: Video unavailable\n", "retried_at": "2026-10-20T17:44:44Z" } ], "retried_at": "2026-10-18T17:12:09Z" }, { "url": "https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z", "src": "https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z", "status": "partial", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=8rXD5-xhemo", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 8rXD5-xhemo: Video unavailable\n", "retried_at": "2026-10-20T17:44:48Z" }, { "url": "https://www.youtube.com/watch?v=kEMJRjEdNzM", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] kEMJRjEdNzM: Video unavailable\n", "retried_at": "2026-10-20T17:44:47Z" }, { "url": "https://www.youtube.com/watch?v=8CWyBNX6eDo", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 8CWyBNX6eDo: Video unavailable\n", "retried_at": "2026-10-20T17:44:48Z" }, { "url": "https://www.youtube.com/watch?v=yLYHDSv-288", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] yLYHDSv-288: Video unavailable\n", "retried_at": "2026-10-20T17:44:46Z" }, { "url": "https://www.youtube.com/watch?v=nC9_RfjYwqA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] nC9_RfjYwqA: Video unavailable\n", "retried_at": "2026-10-20T17:44:49Z" }, { "url": "https://www.youtube.com/watch?v=iWea12EAu6U", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] iWea12EAu6U: Video unavailable\n", "retried_at": "2026-10-20T17:44:53Z" }, { "url": "https://www.youtube.com/watch?v=QEw0qEa0E50", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] QEw0qEa0E50: Video unavailable\n", "retried_at": "2026-10-20T17:44:50Z" }, { "url": "https://www.youtube.com/watch?v=XXtpJxZBa2c", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] XXtpJxZBa2c: Video unavailable\n", "retried_at": "2026-10-20T17:44:54Z" }, { "url": "https://www.youtube.com/watch?v=fyqm8fRDgl0", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] fyqm8fRDgl0: Video unavailable\n", "retried_at": "2026-10-20T17:44:52Z" }, { "url": "https://www.youtube.com/watch?v=yIdF-17HwSk", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] yIdF-17HwSk: Video unavailable\n", "retried_at": "2026-10-20T17:44:53Z" }, { "url": "https://www.youtube.com/watch?v=EAJoRA0KX7I", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] EAJoRA0KX7I: Video unavailable\n", "retried_at": "2026-10-20T17:44:55Z" }, { "url": "https://www.youtube.com/watch?v=9oTHFx0Gg3Q", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 9oTHFx0Gg3Q: Video unavailable\n", "retried_at": "2026-10-20T17:44:56Z" }, { "url": "https://www.youtube.com/watch?v=S-CspeZ8FHc", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] S-CspeZ8FHc: Video unavailable\n", "retried_at": "2026-10-20T17:44:56Z" }, { "url": "https://www.youtube.com/watch?v=5vcj8kSwBCY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 5vcj8kSwBCY: Video unavailable\n", "retried_at": "2026-10-20T17:44:58Z" }, { "url": "https://www.youtube.com/watch?v=4uG1NMKNWCU", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 4uG1NMKNWCU: Video unavailable\n", "retried_at": "2026-10-20T17:45:41Z" }, { "url": "https://www.youtube.com/watch?v=i19m4GzBhfc", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] i19m4GzBhfc: Video unavailable\n", "retried_at": "2026-10-20T17:45:41Z" }, { "url": "https://www.youtube.com/watch?v=M8dsZsEtEsg", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] M8dsZsEtEsg: Video unavailable\n", "retried_at": "2026-10-20T17:45:41Z" }, { "url": "https://www.youtube.com/watch?v=6Z4A3RSf-HY", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 6Z4A3RSf-HY: Video unavailable\n", "retried_at": "2026-10-20T17:45:41Z" }, { "url": "https://www.youtube.com/watch?v=XR8YSRcuVLE", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] XR8YSRcuVLE: Video unavailable\n", "retried_at": "2026-10-20T17:45:45Z" }, { "url": "https://www.youtube.com/watch?v=3wWZBGN-iX8", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] 3wWZBGN-iX8: Video unavailable\n", "retried_at": "2026-10-20T17:45:44Z" }, { "url": "https://www.youtube.com/watch?v=mp95Z5yM92c", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] mp95Z5yM92c: Video unavailable\n", "retried_at": "2026-10-20T17:44:41Z" }, { "url": "https://www.youtube.com/watch?v=knTc-NQSjKA", "status": "source_unavailable", "kind": "single_video", "title": "", "error": "ERROR: [youtube] knTc-NQSjKA: Video unavailable\n", "retried_at": "2026-10-20T17:44:42Z" } ], "retried_at": "2026-10-18T17:12:10Z" }, { "url": "https://www.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6", "src": "https://www.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6", "status": "ok", "kind": "playlist", "items": [ { "url": "https://www.youtube.com/watch?v=OQQ-W_63UgQ", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-OQQ-W_63UgQ.mp4", "bytes": 288601703, "valid": true, "height": 1080, "width": 1920, "duration": "4300.861000", "reused": false, "retried_at": "2026-10-18T18:20:09Z" }, { "url": "https://www.youtube.com/watch?v=ERibwqs9p38", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-ERibwqs9p38.mp4", "bytes": 206668846, "valid": true, "height": 1080, "width": 1920, "duration": "4696.481000", "reused": false, "retried_at": "2026-10-18T18:20:06Z" }, { "url": "https://www.youtube.com/watch?v=ASn7ExxLZws", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-ASn7ExxLZws.mp4", "bytes": 238952473, "valid": true, "height": 1080, "width": 1920, "duration": "4719.361000", "reused": true, "reused_from": "xinxing-zimeiti-corpus/attachments/72f919ad0a05/videos/repair-ASn7ExxLZws.mp4", "retried_at": "2026-10-18T18:19:31Z" }, { "url": "https://www.youtube.com/watch?v=uc2_iwVqrRI", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-uc2_iwVqrRI.mp4", "bytes": 523138012, "valid": true, "height": 1080, "width": 1920, "duration": "4602.661000", "reused": false, "retried_at": "2026-10-18T18:20:46Z" }, { "url": "https://www.youtube.com/watch?v=isPiE-DBagM", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-isPiE-DBagM.mp4", "bytes": 574158547, "valid": true, "height": 1080, "width": 1920, "duration": "4699.981000", "reused": false, "retried_at": "2026-10-18T18:20:32Z" }, { "url": "https://www.youtube.com/watch?v=PVShkZgXznc", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-PVShkZgXznc.mp4", "bytes": 768622910, "valid": true, "height": 1080, "width": 1920, "duration": "4986.141000", "reused": false, "retried_at": "2026-10-18T18:21:22Z" }, { "url": "https://www.youtube.com/watch?v=PicxU81owCs", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-PicxU81owCs.mp4", "bytes": 350809858, "valid": true, "height": 1080, "width": 1920, "duration": "4353.021000", "reused": false, "retried_at": "2026-10-18T18:22:25Z" }, { "url": "https://www.youtube.com/watch?v=Keqep_PKrY8", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-Keqep_PKrY8.mp4", "bytes": 274750794, "valid": true, "height": 1080, "width": 1920, "duration": "4682.541000", "reused": false, "retried_at": "2026-10-18T18:21:22Z" }, { "url": "https://www.youtube.com/watch?v=QuELiw8tbx8", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-QuELiw8tbx8.mp4", "bytes": 176566602, "valid": true, "height": 1080, "width": 1920, "duration": "4827.821000", "reused": false, "retried_at": "2026-10-18T18:22:11Z" }, { "url": "https://www.youtube.com/watch?v=2DYxT4OMAmw", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-2DYxT4OMAmw.mp4", "bytes": 421347953, "valid": true, "height": 1080, "width": 1920, "duration": "5101.061000", "reused": false, "retried_at": "2026-10-18T18:22:08Z" }, { "url": "https://www.youtube.com/watch?v=IxQtK2SjWWM", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-IxQtK2SjWWM.mp4", "bytes": 256003120, "valid": true, "height": 1080, "width": 1920, "duration": "4883.601000", "reused": false, "retried_at": "2026-10-18T18:22:46Z" }, { "url": "https://www.youtube.com/watch?v=6_MO12fPC-0", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-6_MO12fPC-0.mp4", "bytes": 432989859, "valid": true, "height": 1080, "width": 1920, "duration": "4799.481000", "reused": false, "retried_at": "2026-10-18T18:24:24Z" }, { "url": "https://www.youtube.com/watch?v=3MjIkWxXigM", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-3MjIkWxXigM.mp4", "bytes": 156186963, "valid": true, "height": 1080, "width": 1920, "duration": "4594.521000", "reused": false, "retried_at": "2026-10-18T18:23:59Z" }, { "url": "https://www.youtube.com/watch?v=Lg6MZw_OOLI", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-Lg6MZw_OOLI.mp4", "bytes": 377756546, "valid": true, "height": 1080, "width": 1920, "duration": "4931.861000", "reused": false, "retried_at": "2026-10-18T18:25:38Z" }, { "url": "https://www.youtube.com/watch?v=RfwgqPkWZ1w", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-RfwgqPkWZ1w.mp4", "bytes": 499993821, "valid": true, "height": 1080, "width": 1920, "duration": "4927.581000", "reused": false, "retried_at": "2026-10-18T18:24:59Z" }, { "url": "https://www.youtube.com/watch?v=rpwEWLaueRk", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-rpwEWLaueRk.mp4", "bytes": 1193950669, "valid": true, "height": 1080, "width": 1920, "duration": "4845.181000", "reused": false, "retried_at": "2026-10-18T18:26:01Z" }, { "url": "https://www.youtube.com/watch?v=T3octNTE7Is", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-T3octNTE7Is.mp4", "bytes": 628847202, "valid": true, "height": 1080, "width": 1920, "duration": "4694.761000", "reused": false, "retried_at": "2026-10-18T18:27:05Z" }, { "url": "https://www.youtube.com/watch?v=B4v545V3Dq0", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-B4v545V3Dq0.mp4", "bytes": 268617109, "valid": true, "height": 1080, "width": 1920, "duration": "4737.481000", "reused": false, "retried_at": "2026-10-18T18:25:49Z" }, { "url": "https://www.youtube.com/watch?v=JYwNmSe4HqE", "status": "ok", "kind": "single_video", "title": "", "local_path": "attachments/aa5b9c1e53d2/videos/repair-JYwNmSe4HqE.mp4", "bytes": 435079479, "valid": true, "height": 1080, "width": 1920, "duration": "4841.523084", "reused": false, "retried_at": "2026-10-18T18:26:26Z" } ], "retried_at": "2026-10-18T17:12:10Z" } ], "links": [ { "href": "http://nlp.stanford.edu/", "label": "", "type": "a" }, { "href": "http://stanford.edu/", "label": "", "type": "a" }, { "href": "https://cs.stanford.edu/~diyiy/", "label": "Diyi Yang", "type": "a" }, { "href": "https://yejinc.github.io/", "label": "Yejin Choi", "type": "a" }, { "href": "https://juliekallini.com/", "label": "Julie Kallini (Head TA)", "type": "a" }, { "href": "https://ai.stanford.edu/~ahmedah/", "label": "Ahmed Ahmed", "type": "a" }, { "href": "https://davidanugraha.github.io/", "label": "David Anugraha", "type": "a" }, { "href": "https://lukebailey181.github.io/", "label": "Luke Bailey", "type": "a" }, { "href": "https://scholar.google.com/citations?user=IVnb6XQAAAAJ&hl=en", "label": "Sarah Chen", "type": "a" }, { "href": "https://cchoi1.github.io/", "label": "Caroline Choi", "type": "a" }, { "href": "https://www.linkedin.com/in/advitdeepak/", "label": "Advit Deepak", "type": "a" }, { "href": "https://www.linkedin.com/in/nevingeorge4", "label": "Nevin George", "type": "a" }, { "href": "https://sekim12.github.io/", "label": "Simon Kim", "type": "a" }, { "href": "https://www.linkedin.com/in/ali-sartaz-khan-9334011a3/", "label": "Ali Sartaz Khan", "type": "a" }, { "href": "https://arpandeep.com/", "label": "Arpandeep Khatua", "type": "a" }, { "href": "https://www.linkedin.com/in/alisa-levin/", "label": "Alisa Levin", "type": "a" }, { "href": "https://george1459.github.io/", "label": "Shicheng Liu", "type": "a" }, { "href": "https://liuwei283.github.io/", "label": "Wei Liu", "type": "a" }, { "href": "https://minsik-ai.github.io/", "label": "Minsik Oh", "type": "a" }, { "href": "https://noviscl.github.io/", "label": "Chenglei Si", "type": "a" }, { "href": "https://sites.google.com/view/msuzgun", "label": "Mirac Suzgun", "type": "a" }, { "href": "http://www.tristanthrush.com/", "label": "Tristan Thrush", "type": "a" }, { "href": "https://smiles724.github.io/", "label": "Fang Wu", "type": "a" }, { "href": "https://yuqinan.github.io/", "label": "Qinan Yu", "type": "a" }, { "href": "https://goo.gl/maps/hRjQYd6MqxB2", "label": "NVIDIA Auditorium", "type": "a" }, { "href": "https://canvas.stanford.edu/", "label": "Canvas", "type": "a" }, { "href": "https://canvas.stanford.edu/courses/217005/external_tools/69960", "label": "Canvas", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D", "label": "the CS224N 2024 YouTube\n playlist", "type": "a" }, { "href": "https://online.stanford.edu/courses/xcs224n-natural-language-processing-deep-learning", "label": "XCS224N: Natural\n Language Processing with Deep Learning", "type": "a" }, { "href": "https://online.stanford.edu/courses/cs224n-natural-language-processing-deep-learning", "label": "CS224N via Stanford\n online", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/office_hours.html", "label": "here", "type": "a" }, { "href": "https://pytorch.org/", "label": "Pytorch", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1254/", "label": "Winter 2025", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246", "label": "Spring 2024", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1244", "label": "Winter 2024", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234", "label": "Winter 2023", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1224", "label": "Winter 2022", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1214", "label": "Winter 2021", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1204", "label": "Winter 2020", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1194", "label": "Winter 2019", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184", "label": "Winter 2018", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174", "label": "Winter 2017", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1162", "label": "Autumn 2015", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1152", "label": "Autumn 2014", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1142", "label": "Autumn 2013", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1132", "label": "Autumn 2012", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1122", "label": "Autumn 2011", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1114", "label": "Winter 2011", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1106", "label": "Spring 2010", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1096", "label": "Spring 2009", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1086", "label": "Spring 2008", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1076", "label": "Spring 2007", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1066", "label": "Spring 2006", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1056", "label": "Spring 2005", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1046", "label": "Spring 2004", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1036", "label": "Spring 2003", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1026", "label": "Spring 2002", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/manning.499", "label": "Spring 2000", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4", "label": "Winter 2023", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ", "label": "Winter 2021", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z", "label": "Winter 2019", "type": "a" }, { "href": "https://www.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6", "label": "Winter 2017", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1244/project.html", "label": "Winter 2024", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1234/project.html", "label": "Winter 2023", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1224/project.html", "label": "Winter 2022", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1214/project.html", "label": "Winter 2021", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1204/project.html", "label": "Winter 2020", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1194/project.html", "label": "Winter 2019", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184/reports.html", "label": "Winter 2018", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/reports.html", "label": "Winter 2017", "type": "a" }, { "href": "http://nlp.stanford.edu/courses/cs224n/", "label": "Autumn 2015 and earlier", "type": "a" }, { "href": "http://cs224d.stanford.edu/reports_2016.html", "label": "Spring 2016", "type": "a" }, { "href": "http://cs224d.stanford.edu/reports_2015.html", "label": "Spring 2015", "type": "a" }, { "href": "https://numpy.org/", "label": "NumPy", "type": "a" }, { "href": "https://web.archive.org/web/20250114002202/http://ciml.info/dl/v0_99/ciml-v0_99-all.pdf", "label": "A Course in Machine Learning", "type": "a" }, { "href": "https://web.stanford.edu/~jurafsky/slp3/", "label": "Speech and Language Processing (2024 pre-release)", "type": "a" }, { "href": "https://github.com/jacobeisenstein/gt-nlp-class/blob/master/notes/eisenstein-nlp-notes.pdf", "label": "Natural Language Processing", "type": "a" }, { "href": "http://u.cs.biu.ac.il/~yogo/nnlp.pdf", "label": "A Primer on Neural Network Models for Natural Language Processing", "type": "a" }, { "href": "http://www.deeplearningbook.org/", "label": "Deep Learning", "type": "a" }, { "href": "https://searchworks.stanford.edu/view/13241676", "label": "Natural Language Processing with PyTorch", "type": "a" }, { "href": "https://transformersbook.com/", "label": "Natural Language Processing with Transformers", "type": "a" }, { "href": "http://neuralnetworksanddeeplearning.com/", "label": "Neural Networks and Deep Learning", "type": "a" }, { "href": "https://mitpress.mit.edu/books/introduction-deep-learning", "label": "Introduction to Deep Learning", "type": "a" }, { "href": "https://www.gradescope.com/courses/1208404", "label": "Gradescope", "type": "a" }, { "href": "https://ed.stanford.edu/academics/masters-handbook/honor-code", "label": "Honor Code", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1246/project.html", "label": "Spring 2024 website", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture06-final-project.pdf", "label": "lecture slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project/custom-final-project-tips.pdf", "label": "custom project tips", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project_w25/CS_224n__Default_Final_Project__Build_GPT_2.pdf", "label": "handout", "type": "a" }, { "href": "https://vaden.stanford.edu/caps-and-wellness", "label": "Counseling and Psychological Services (CAPS)", "type": "a" }, { "href": "https://oae.stanford.edu/", "label": "Office of Accessible Education (OAE)", "type": "a" }, { "href": "https://communitystandards.stanford.edu/generative-ai-policy-guidance", "label": "here", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/are recovering from", "label": "https://vaden.stanford.edu/sexual-assault", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture01-intro.pdf", "label": "intro slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture01-history.pdf", "label": "history slides", "type": "a" }, { "href": "https://www.amacad.org/publication/daedalus/human-language-understanding-reasoning", "label": "Human Language Understanding & Reasoning", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a1.zip", "label": "code", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture02-wordvecs.pdf", "label": "slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/cs224n_winter2023_lecture1_notes_draft.pdf", "label": "notes 1", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes02-wordvecs2.pdf", "label": "notes 2", "type": "a" }, { "href": "http://arxiv.org/pdf/1301.3781.pdf", "label": "Efficient Estimation of Word Representations in Vector Space", "type": "a" }, { "href": "http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf", "label": "Distributed Representations of Words and Phrases and their Compositionality", "type": "a" }, { "href": "http://nlp.stanford.edu/pubs/glove.pdf", "label": "GloVe: Global Vectors for Word Representation", "type": "a" }, { "href": "http://www.aclweb.org/anthology/Q15-1016", "label": "Improving Distributional Similarity with Lessons Learned from Word Embeddings", "type": "a" }, { "href": "http://www.aclweb.org/anthology/D15-1036", "label": "Evaluation methods for unsupervised word embeddings", "type": "a" }, { "href": "http://aclweb.org/anthology/Q16-1028", "label": "A Latent Variable Model Approach to PMI-based Word Embeddings", "type": "a" }, { "href": "https://transacl.org/ojs/index.php/tacl/article/viewFile/1346/320", "label": "Linear Algebraic Structure of Word Senses, with Applications to Polysemy", "type": "a" }, { "href": "https://papers.nips.cc/paper/7368-on-the-dimensionality-of-word-embedding.pdf", "label": "On the Dimensionality of Word Embedding", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w25/2024 CS224N Python Review Session Slides.pptx.pdf", "label": "slides", "type": "a" }, { "href": "https://colab.research.google.com/drive/1hxWtr98jXqRDs_rZLZcEmX_hUcpDLq6e?usp=sharing", "label": "colab", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture03-neuralnets.pdf", "label": "slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes03-neuralnets.pdf", "label": "notes", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/gradient-notes.pdf", "label": "matrix calculus notes", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/review-differential-calculus.pdf", "label": "Review of differential calculus", "type": "a" }, { "href": "http://cs231n.github.io/neural-networks-1/", "label": "CS231n notes on network architectures", "type": "a" }, { "href": "http://cs231n.github.io/optimization-2/", "label": "CS231n notes on backprop", "type": "a" }, { "href": "http://cs231n.stanford.edu/handouts/derivatives.pdf", "label": "Derivatives, Backpropagation, and Vectorization", "type": "a" }, { "href": "http://www.iro.umontreal.ca/~vincentp/ift3395/lectures/backprop_old.pdf", "label": "Learning Representations by Backpropagating Errors", "type": "a" }, { "href": "https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b", "label": "Yes you should understand backprop", "type": "a" }, { "href": "http://www.jmlr.org/papers/volume12/collobert11a/collobert11a.pdf", "label": "Natural Language Processing (Almost) from Scratch", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a2.zip", "label": "code", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a2.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a2_tex.zip", "label": "latex template", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture04-rnnlm.pdf", "label": "slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes05-LM_RNN.pdf", "label": "notes", "type": "a" }, { "href": "https://ieeexplore.ieee.org/document/279181", "label": "Learning long-term dependencies with gradient descent is difficult", "type": "a" }, { "href": "https://arxiv.org/pdf/1211.5063.pdf", "label": "On the difficulty of training Recurrent Neural Networks", "type": "a" }, { "href": "https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/lectures/vanishing_grad_example.html", "label": "Vanishing Gradients Jupyter Notebook", "type": "a" }, { "href": "https://arxiv.org/abs/1706.03762.pdf", "label": "Attention Is All You Need", "type": "a" }, { "href": "https://colab.research.google.com/drive/1Pz8b_h-W9zIBk1p2e6v-YFYThG1NkYeS?usp=sharing", "label": "colab", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture05-transformers.pdf", "label": "slides", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/readings/cs224n-self-attention-transformers-2023_draft.pdf", "label": "notes", "type": "a" }, { "href": "https://jalammar.github.io/illustrated-transformer/", "label": "The Illustrated Transformer", "type": "a" }, { "href": "https://ai.googleblog.com/2017/08/transformer-novel-neural-network.html", "label": "Transformer (Google AI blog post)", "type": "a" }, { "href": "https://arxiv.org/pdf/1607.06450.pdf", "label": "Layer Normalization", "type": "a" }, { "href": "https://arxiv.org/pdf/1802.05751.pdf", "label": "Image Transformer", "type": "a" }, { "href": "https://arxiv.org/pdf/1809.04281.pdf", "label": "Music Transformer: Generating music with long-term structure", "type": "a" }, { "href": "https://web.stanford.edu/~jurafsky/slp3/9.pdf", "label": "Jurafsky and Martin Chapter 9 (The Transformer)", "type": "a" }, { "href": "https://www.deeplearningbook.org/contents/guidelines.html", "label": "Practical Methodology", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a3.zip", "label": "code", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a3.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a3_tex.zip", "label": "latex template", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture07-pretraining.pdf", "label": "slides", "type": "a" }, { "href": "https://arxiv.org/pdf/1810.04805.pdf", "label": "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", "type": "a" }, { "href": "https://arxiv.org/abs/1902.06006.pdf", "label": "Contextual Word Representations: A Contextual Introduction", "type": "a" }, { "href": "http://jalammar.github.io/illustrated-bert/", "label": "The Illustrated BERT, ELMo, and co.", "type": "a" }, { "href": "https://web.stanford.edu/~jurafsky/slp3/10.pdf", "label": "Jurafsky and Martin Chapter 10 (Masked Language Models)", "type": "a" }, { "href": "https://arxiv.org/abs/2407.21783", "label": "The Llama 3 Herd of Models", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture08-posttraining.pdf", "label": "slides", "type": "a" }, { "href": "https://openai.com/research/instruction-following", "label": "Aligning language models to follow instructions", "type": "a" }, { "href": "https://arxiv.org/abs/2210.11416", "label": "Scaling Instruction-Finetuned Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/2305.14387", "label": "AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback", "type": "a" }, { "href": "https://arxiv.org/abs/2306.04751", "label": "How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources", "type": "a" }, { "href": "https://arxiv.org/abs/2305.18290", "label": "Direct Preference Optimization: Your Language Model is Secretly a Reward Model", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project/Project_Proposal_Instructions.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project/DFP_Instructions.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture09-peft.pdf", "label": "slides", "type": "a" }, { "href": "https://arxiv.org/abs/2005.14165", "label": "Language Models are Few-Shot Learners", "type": "a" }, { "href": "https://arxiv.org/abs/2201.11903", "label": "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/1803.03635", "label": "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks", "type": "a" }, { "href": "https://arxiv.org/abs/2106.09685", "label": "LoRA: Low-Rank Adaptation of Large Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/1902.00751", "label": "Parameter-Efficient Transfer Learning for NLP", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture10-rag-agents.pdf", "label": "slides", "type": "a" }, { "href": "https://arxiv.org/abs/2210.03629", "label": "ReAct: Synergizing Reasoning and Acting in Language Models", "type": "a" }, { "href": "https://language-agent-tutorial.github.io/", "label": "Language Agents: Foundations, Prospects, and Risks", "type": "a" }, { "href": "https://arxiv.org/abs/2005.11401", "label": "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks", "type": "a" }, { "href": "https://arxiv.org/abs/2302.04761", "label": "Toolformer: Language Models Can Teach Themselves to Use Tools", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a4.zip", "label": "code", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a4.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/assignments_w26/a4_tex.zip", "label": "latex template", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/materials/hf_transformers_tutorial.pdf", "label": "slides", "type": "a" }, { "href": "https://colab.research.google.com/drive/1FyCMNTXfirWbJ18GuIT_JiTW0gwrxI3O?usp=sharing", "label": "colab", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture11-evaluation.pdf", "label": "slides", "type": "a" }, { "href": "https://www.ruder.io/nlp-benchmarking/", "label": "Challenges and Opportunities in NLP Benchmarking", "type": "a" }, { "href": "https://arxiv.org/abs/2009.03300", "label": "Measuring Massive Multitask Language Understanding", "type": "a" }, { "href": "https://arxiv.org/abs/2211.09110", "label": "Holistic Evaluation of Language Models", "type": "a" }, { "href": "https://tatsu-lab.github.io/alpaca_eval/", "label": "AlpacaEval", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture12-reasoning-part1.pdf", "label": "slides", "type": "a" }, { "href": "https://arxiv.org/abs/2203.11171", "label": "Self-Consistency Improves Chain of Thought Reasoning in Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/2501.12948", "label": "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning", "type": "a" }, { "href": "https://arxiv.org/abs/2503.14476", "label": "DAPO: An Open-Source LLM Reinforcement Learning System at Scale", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture13-reasoning-part2.pdf", "label": "slides", "type": "a" }, { "href": "https://arxiv.org/abs/2305.20050", "label": "Let's Verify Step by Step", "type": "a" }, { "href": "https://arxiv.org/abs/2211.17192", "label": "Fast Inference from Transformers via Speculative Decoding", "type": "a" }, { "href": "https://arxiv.org/abs/2408.03314", "label": "Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters", "type": "a" }, { "href": "https://arxiv.org/abs/2104.09864", "label": "RoFormer: Enhanced Transformer with Rotary Position Embedding", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project/Project_Milestone_Instructions.pdf", "label": "handout", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture14-guest-julie-tokenization-multilinguality.pdf", "label": "slides", "type": "a" }, { "href": "https://web.stanford.edu/~jurafsky/slp3/2.pdf", "label": "Jurafsky & Martin Chapter 2", "type": "a" }, { "href": "https://arxiv.org/pdf/1508.07909", "label": "Neural Machine Translation of Rare Words with Subword Units", "type": "a" }, { "href": "https://aclanthology.org/2020.acl-main.747.pdf", "label": "Unsupervised Cross-lingual Representation Learning at Scale", "type": "a" }, { "href": "https://aclanthology.org/2023.emnlp-main.614.pdf", "label": "Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models", "type": "a" }, { "href": "https://beenkim.github.io/", "label": "Been Kim", "type": "a" }, { "href": "https://arxiv.org/abs/2506.12152", "label": "Because we have LLMs, we Can and Should Pursue Agentic Interpretability", "type": "a" }, { "href": "https://medium.com/@beenkim/the-pareto-frontier-of-human-centered-ai-54f90ba5872c", "label": "The Pareto Frontier of Human-Centered AI", "type": "a" }, { "href": "https://www.pnas.org/doi/10.1073/pnas.2406675122", "label": "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero", "type": "a" }, { "href": "https://arxiv.org/abs/2502.07586", "label": "We Can't Understand AI Using our Existing Vocabulary", "type": "a" }, { "href": "https://arxiv.org/abs/2510.08506", "label": "Neologism Learning for Controllability and Self-Verbalization", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/project/Project_Report_Instructions.pdf", "label": "Instructions", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture16-impact-on-humanity.pdf", "label": "slides", "type": "a" }, { "href": "https://homes.cs.washington.edu/~lsz/", "label": "Luke Zettlemoyer", "type": "a" }, { "href": "https://visualsketchpad.github.io/", "label": "Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/2405.09818", "label": "Chameleon: Mixed-Modal Early-Fusion Foundation Models", "type": "a" }, { "href": "https://arxiv.org/abs/2408.11039", "label": "Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model", "type": "a" }, { "href": "https://arxiv.org/abs/2411.04996", "label": "Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models", "type": "a" }, { "href": "https://arxiv.org/abs/2301.03728", "label": "Scaling Laws for Generative Mixed-Modal Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/2309.02591", "label": "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", "type": "a" }, { "href": "https://arxiv.org/abs/2211.12561", "label": "Retrieval Augmented Multimodal Language Modeling", "type": "a" }, { "href": "https://arxiv.org/abs/2412.15188", "label": "LMFusion: Adapting Pretrained Language Models for Multimodal Generation", "type": "a" }, { "href": "https://arxiv.org/abs/2510.03506", "label": "OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows", "type": "a" }, { "href": "https://arxiv.org/abs/2502.14191", "label": "Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models", "type": "a" }, { "href": "https://arxiv.org/abs/2509.07295", "label": "Reconstruction Alignment Improves Unified Multimodal Models", "type": "a" }, { "href": "http://joschu.net/", "label": "John Schulman", "type": "a" }, { "href": "https://web.stanford.edu/class/cs224n/slides_w26/cs224n-2026-lecture19-open-questions.pdf", "label": "slides", "type": "a" }, { "href": "https://docs.google.com/document/d/1J8-TVVvndimSwq3jGzpMO_OtPAx_EaU9nUiiPUQdVpY", "label": "Printing guide", "type": "a" } ], "repair_version": 2, "repaired_at": "2026-10-14T10:54:05Z", "source_url": "https://web.stanford.edu/class/cs224n/", "papers": [ { "status": "ok", "url": "https://web.archive.org/web/20250114002202/http://ciml.info/dl/v0_99/ciml-v0_99-all.pdf", "bytes": 3921784, "reused": false, "local_path": "papers/repair/6e202195917f093d45e1.pdf" }, { "status": "ok", "url": "https://raw.githubusercontent.com/jacobeisenstein/gt-nlp-class/master/notes/eisenstein-nlp-notes.pdf", "bytes": 3359237, "reused": false, "local_path": "papers/repair/dcd5fa1ad1db8a583461.pdf" }, { "status": "download_error", "url": "http://u.cs.biu.ac.il/~yogo/nnlp.pdf", "reason": "ConnectTimeout: HTTPConnectionPool(host='u.cs.biu.ac.il', port=80): Max retries exceeded with url: /~yogo/nnlp.pdf (Caused by ConnectTimeoutError(