CMSC848O

Selected Topics in Information Processing; Long-Context Language Models

Focuses on recent developments in training, aligning, and evaluating long-context language models, which have allowed cutting-edge LLMs to process and generate millions of words. Topics include neural architectures (e.g., Transformers, Mamba), extended context fine-tuning/upscaling, and tasks such as summarization and QA over books.

Sister Courses: CMSC848B, CMSC848C, CMSC848D, CMSC848E, CMSC848F, CMSC848G, CMSC848I, CMSC848J, CMSC848K, CMSC848M, CMSC848N, CMSC848P, CMSC848Q, CMSC848R, CMSC848T, CMSC848U, CMSC848W, CMSC848Z

Spring 2025

0 reviews
Average rating: N/A

During the Spring 2020 and Spring 2021 semesters, students could choose to take some of their courses pass-fail mid-semester which skews grade data aggregated across multiple semesters.

Average GPA of 3.75 between 50 students*

CMSC848O Grade Distribution+-0510152025303540455055606570% of studentsABCDFWother
A-: 14%
A: 52%
B: 8%
B+: 14%
other: 12%
* "W"s are considered to be 0.0 quality points. "Other" grades are not factored into GPA calculation. Grade data not guaranteed to be correct.