Resources
We value reproducible and open science.
Software tools
-
Context-Adaptive ML:
-
: An SKLearn-style toolbox for estimating and analyzing models, distributions, and functions with context-specific parameters
-
-
Tools for large-scale, distributed, parallel, sparsity in LMs. Includes: - FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
- PiKV: KV Cache Management System for MoE
- GraphSnapShot: Caching Local Structure for Fast Graph Learning
- MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
- CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient LLM Inference
-
Explainable Boosting Machines (EBM):
- TalkToEBM - A Natural Language Interface to Explainable Boosting Machines (EBMs)
- EBM Utils - Utilities for EBM
- GAM Purification - Tools for purifying additive models with interaction effects into identifiable representations.
- Academic Utils:
- ConferenceCountdown - A countdown website for ML/CompBio conference deadlines.
- website_utils - Some utilities for building this website.
Advice
- Thoughts from my Faculty Application Experience
- A few lessons learned from a few years in ML research
- Advice to Prospective Students
- Joining the Lab (current UW-Madison students, postdocs, and collaborators)
- Advice on Letters of Recommendation, including how to request a letter from me
Classic reading on doing research
- Richard Hamming, You and Your Research (1986)
- William Shockley, On the Statistics of Individual Variations of Productivity in Research Laboratories, Proceedings of the IRE (1957)
- Marian Petre and Gordon Rugg, The Unwritten Rules of PhD Research (Open University Press)
Compilations
Templates
- Latex templates for faculty applications
- Latex template for preprints
- Latex template for academic CV