Archive
Review
The graduate follow-up to EECS 183. As promised, CS 288 focused on transformers and LLMs. The first unit built up LLM architecture to Llama 3. The next unit was retrieval with RAG, and the associated assignment was rather creative: build a RAG QA system for the EECS directory, doing all of the scraping and chunking by hand. The final unit got us from Llama 3 to 2026 SOTA by covering MoE, RLHF, agents, and test time compute.
Prof. Min is a young, lively addition to Berkeley NLP (I think she comes across as a bit of a workaholic) and she put a lot of effort in modernizing the curriculum. Unfortunately, Prof. Suhr ended up reusing much of her 183 slides, so I didn’t end up learning much when she lectured.
For the final research paper, my teammates and I created a multimodal RAG system for lecture videos, then rendering animation-dense instructional videos post-retrieval.
CS 288 was a rather project-heavy class, 3.5/5 in difficulty and 4.5/5 in fun.