A concise canon of foundational papers in ML, systems, NLP, speech, and audio
deliprao · x · 2026-07-27
A compact reading list of foundational papers across ML, systems, and NLP
In response to a question about the most influential papers to revisit, the author lists a personal canon by area:
- ML: Partha’s manifold regularization paper; Jerry Xu’s label propagation paper
- ML/data systems: Jeff Dean and Sanjay’s MapReduce paper
- NLP: the “one sense per discourse” paper; Brown, Della Pietra, and Mercer’s SMT paper
- Applied NLP: Hearst patterns
- Speech: Hinton et al. on DNN acoustic modeling
- Audio: Urban Sounds; YT8M
It’s essentially a terse but useful map of seminal work the author keeps returning to for education and reference.
More from Research
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- TechCrunch says brain-wave signals could be the next unlock for physical AI training — TechCrunch AI · 2026-07-27
- NeurIPS Rebuttal Deadline Approaches: Tips for Writing High-Quality Responses — furongh · 2026-07-27
- A computer science paper titled “In Cantor Space No One Can Hear You Stream” — fkasummer · 2026-07-27
- YC talk says robots need better pretraining, memory, and compositional behaviors — ycombinator · 2026-07-27