Skip to content
All tags

#cs224n

20 posts

CS224N Lecture 3: Matrix Calculus and Backpropagation

Lecture 3 decomposes neural-network training into computation graphs, local derivatives, and the chain rule: the forward pass computes a result; backprop accumulates gradients from the output so every parameter knows how to move.

CS224N Lecture 11: Why LLM Benchmarks Expire

Lecture 11 divides evaluation into what to test, how to measure it, and when the result stops being trustworthy. Benchmarks saturate or leak, prompts change scores, and an LLM judge remains a biased model.

CS224N Lecture 9: Prompting, LoRA, and Parameter-Efficient Adaptation

Lecture 9 compares prompting, pruning, LoRA, prompt tuning, and adapters. Each asks the same question: how many parameters must change, and how much task-specific state must be stored, to adapt a large pretrained model?

CS224N Lecture 6: Turn a Final Project into a Testable Question

Lecture 6 completes the Transformer picture with encoders, decoders, and cross-attention, then breaks the final project into formats, assessment, research topics, and data. A viable topic needs one explicit baseline and metric.

CS224N Lecture 1: Four Paradigm Shifts in NLP

Winter 2026 Lecture 1 divides NLP into four eras: early exploration, symbolic systems, statistical machine learning, and deep/self-supervised learning. The point is not the dates but how each era redefined the language problem.

CS224N Lecture 15: Reading Agentic Interpretability Without Public Slides

Lecture 15 is Been Kim's interpretability guest session, but the Winter 2026 site publishes no slides or agenda. This article does not invent lecture content; it maps the five official readings across concept discovery, agentic investigation, and new vocabulary.

CS224N Lecture 17: An Official Reading Map for Multimodality

Lecture 17 is Luke Zettlemoyer's multimodality guest session, but the site publishes no slides or agenda. Its official readings establish three routes: visual reasoning workspaces, early-fusion token models, and text autoregression with image diffusion.

CS224N Lecture 19: How Small Models Can Move Beyond Brute-Force Scaling

The final lecture frames Open Questions in NLP 2026 as smart scaling: prolonged RL, Prismatic synthetic data, RL as pretraining, and open collaboration seek reasoning gains beyond adding parameters.

CS224N Lecture 8: From Instruction Tuning and RLHF to DPO

Lecture 8 explains how instruction tuning, preference data, and RLHF turn a pretrained model into an assistant, then derives DPO from winner–loser pairs. Every step converts human judgment into signal—and imports its biases.

CS224N Lecture 7: Pretraining, Subwords, and In-Context Learning

Lecture 7 decomposes pretraining into scalable data, subword tokenization, three model objectives, and in-context learning. A general self-supervised objective yields reusable representations; downstream signals specify their use.

CS224N Lecture 10: Six Components of RAG and Language Agents

Lecture 10 moves from question answering and RAG into language agents, then decomposes them into reasoning and planning, memory, tools, data, and evaluation. An agent is an inspectable loop between a model and external state.

CS224N Lecture 12: Decoding, DeepSeek-R1, and Reasoning Training

Lecture 12 shows that output policy is not a detail: greedy, beam, and sampling produce different text. It then moves from R1-Zero/R1 into PPO, GRPO, and DAPO, asking when longer reasoning actually helps.

CS224N Lecture 13: Speculative Decoding and Test-Time Scaling

Lecture 13 moves from inference efficiency to inference capability: speculative decoding drafts with a small model and verifies with a large one; on-policy distillation addresses drift; long context and test-time scaling spend inference resources.

CS224N Lecture 4: Language Models, RNNs, and Vanishing Gradients

Lecture 4 defines a language model as a next-word probability distribution, then uses an RNN to compress an arbitrarily long prefix. It also exposes recurrence's central cost: information and gradients travel one time step at a time.

CS224N Lecture 16: Hallucination, Creativity, Work, and Alignment

Lecture 16 divides NLP's social impact into four questions: why models hallucinate, why AI-assisted creativity may homogenize output, how work is reorganized, and why value alignment cannot be reduced to one reward.

CS224N Lecture 18: Material-Gap Record for Tinker and LoRA Without Regret

Lecture 18 is a John Schulman guest session. The official page gives only the title Tinker and LoRA Without Regret, date, and speaker—no slides, agenda, or readings—so this article records confirmed facts and unknowns only.

CS224N Lecture 14: How Tokenization Creates Multilingual Cost Gaps

Lecture 14 moves from word, character/byte, and subword segmentation to BPE failures and cross-lingual fairness. A tokenizer determines sequence length, compute cost, and the units a model sees; it is not neutral preprocessing.

CS224N Lecture 5: From Recurrence to the Transformer

Lecture 5 moves from the long-range and sequential bottlenecks of RNNs to self-attention and the Transformer. It shortens information paths and enables parallel computation, at the price of quadratic attention and separately encoded position.

CS224N Lecture 2: How word2vec Turns Meaning into Vectors

Lecture 2 moves from word2vec's prediction task, objective, and gradients to count-based vectors and evaluation. Meaning becomes a high-dimensional position learned from context, not a label retrieved from a dictionary.

Stanford CS224N: Open the 2019 Syllabus and Transformers Are Still Lecture 14

CS224N has kept every course website since 2000 online. In Winter 2019, Transformers were lecture 14, taught by a guest. In Winter 2026 they are lecture 5, and every lecture after that assumes you already know them. The machine translation assignment is gone; assignment 3 now has you code a decoder-only Transformer from scratch, with pytest suites that run on your laptop.