| day | topic | resources | details |
| Apr 25 | introduction | organization, lectures, student topics | |
| May 2 | no class | ||
| May 9 | synthetic data | talk by Latif Köksal, DeepMind | |
| May 16 | discussion of topics | ||
| scheduling | |||
| May 23 | memory etc. | NoLiMa | talk by Ali Modaresi |
| May 30 | refusal | paper | |
| June 6 | |||
| Jun 13 | |||
| Jun 20 | |||
| Jun 27 | |||
| Jul 4 | |||
| Jul 11 | |||
| Jul 18 | multilingual reasoning | Mingyang Wang | paper |
| Jul 25 | formal methods for LLMs | William Merrill, NYU |
arch = architectures, including agentic systems and human-agent collaboration
reas = reasoning
interp = interpretability
tech = technical report
eval = evaluation
synth = synthetic data
misc = miscellaneous
| paper | topic | |||
| all topics covered in the lectures (see above) | ||||
| reas | Geiping et al. (2025) | test-time compute: recurrent depth approach | ||
| reas | DeepSeek-AI (2025) | DeepSeek-R1: reasoning through RL | ||
| tech | Gemma Team (2025) | Gemma 3 technical report | ||
| interp | Olsson et al. (2022) | induction heads | ||
| synth | Maini et al. (2024) | rephrasing the web | ||
| interp | Sharkey et al. (2025) | open problems in mechanistic interpretability | ||
| interp | Park et al. (2024) | linear representation hypothesis | ||
| interp | Han et al. (2024) | word embeddings are steers | ||
| tech | Llama Team (2024) | Llama 4 | ||
| tech | Llama Team (2024) | Llama 3 | ||
| tech | Xu et al. (2025) | Qwen 2.5-Omni | ||
| tech | Bai et al. (2025) | Qwen 2.5-VL | ||
| tech | Qwen et al. (2024) | Qwen 2.5 | ||
| tech | Abdin et al. (2024) | Phi-4 | ||
| interp | Makelov et al. (2024) | sparse autoencoders (2) | ||
| interp | McDougall et al. (2023) | copy suppression | ||
| interp | Saphra et al. (2024) | notion of mechinterp | ||
| reas | Dutta et al. (2024) | mechinterp: COT | ||
| interp | Geva et al. (2023) | factual associations/enrichment | ||
| interp | nostalgebrist (2020) | logit lens | ||
| interp | Chughtai et al. (2024) | summing up the facts | ||
| reas | Shao et al. (2024) | DeepSeekMath | ||
| reas | Zhao et al. (2024) | Marco-o1 | ||
| arch | Wu et al. (2024) | REFT | ||
| reas | Hübotter et al. (2025) | SIFT | ||
| misc | Hughes et al. (2024) | open-endedness | ||
| reas | Turpin et al. (2023) | unfaithful COT | ||
| arch | Gottweis et al. (2025) | AI co-scientist | ||
| reas | Venhoff et al. (2025) | steered reasoning | ||
| interp | Yu et al. (2024) | superweights | ||
| interp | Bricken et al. (2023) | sparse autoencoders (1) | ||
| arch | Packer et al. (2023) | MemGPT | ||
| misc | Milliere et al. (2024) | philosophy of LLMs | ||
| arch | StanfordNLP (2024) | DSPy | ||
| interp | Durrani et al. (2020) | analyzing neurons | ||
| interp | Voita et al. (2023) | dead neurons | ||
| arch | De Peuter et al. (2023) | human-agent cooperation | ||
| tech | Ustun et al. (2024) | Aya | ||
| tech | NotebookLM | |||
| tech | Groeneveld et al. (2024) | Olmo | ||
| interp | Dai et al. (2022) | knowledge neurons | ||
| interp | Elhelo et al. (2024) | head functionality | ||
| interp | Ferrando et al. (2024) | information flow routes | ||
| misc | Nancy Yu (2024) | llm censorship | ||
| interp | Lad et al. (2024) | stages of inference | ||
| interp | Geva et al. (2021) | llms as key value memories | ||
| interp | Wendler et al. (2024) | multilingual representations | ||
| tech | Anthropic (2025) PR | Claude 3.7 Sonnet | ||
| tech | DeepSeek-AI (2025) | DeepSeek V3 | ||
| interp | Lindsey et al. (2025) | biology of LLMs | ||
| eval | Phan et al. (2025) | humanity's last exam | ||
| tech | Team Cohere (2025) | Command A | ||
| misc | Asai et al. (2023) | Self-RAG | ||
| misc | Xu et al. (2024) | ActiveRAG | ||
| misc | Jeong et al. (2024) | Adaptive-RAG | ||
