csinva/vscode-browser-html-preview
Preview static HTML pages inside VS Code tabs, served by the Live Server extension, without opening a browser
Seeking superhuman explanations. Prev @MicrosoftResearch & AI PhD from UC Berkeley.
Repositories
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
csinva/matching-with-gans
Matching in GAN latent space for better bias benchmarking and semantic image editing. 👶🏻🧒🏾👩🏼🦰👱🏽♂️👴🏾
csinva/agentic-imodels
Agent-interpretable data-science tools, evolved via autoresearch (NeurIPS 2026).
csinva/csinva.github.io
Slides, paper notes, class notes, blog posts, and research on ML 📉, statistics 📊, and AI 🤖.
csinva/agent-progress
tqdm-style progress bars in the Claude Code statusline for any long-running job. Claude picks how to observe progress; the ETA corrects itself; crashes come back with a skull and a report.
csinva/imodelsX
Interpret text data with LLMs (sklearn compatible).
csinva/gpt-paper-title-generator
Generating paper titles (and more!) with GPT trained on data scraped from arXiv.
csinva/gan-vae-pretrained-pytorch
Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.
csinva/emmet-cube-public
csinva/transformation-importance
Using / reproducing TRIM from the paper "Transformation Importance with Applications to Cosmology" 🌌 (ICLR Workshop 2020)
csinva/hpa-interp
Interpretations on the HPA dataset.
csinva/hierarchical-dnn-interpretations
Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
csinva/tree-prompt
Tree prompting: easy-to-use scikit-learn interface for improved prompting.
csinva/iprompt
Finding semantically meaningful and accurate prompts.
csinva/csinva
readme
csinva/circuit-building-autoresearch
Let the agent write the weights, why not?
csinva/quick-quiz
Clean website for simple self-quizzing.
csinva/automated-brain-explanations
Generating and validating natural-language explanations for the brain.
csinva/copilot-keepgoing
Automatically message copilot cli to keep going whenever it stops (useful for autoresearch loops).
csinva/interpretable-embeddings
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
csinva/pyfim-clone
Clone of pyfim making it installable as a dependency. Copied from http://www.borgelt.net/pyfim.html
csinva/cookiecutter-ml-research
A logical, reasonably standardized, but flexible project structure for conducting ml research 🍪
csinva/news-balancer
News Balancer takes a story and provides articles on that story with credibility and varying political bias. The homepage will randomly generate a story from its archives, but a user can type in a query to get stories relating to their query along with their credibility / political bias.
csinva/disentangled-attribution-curves
Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"
csinva/dnn-ensemble
Testing the properties of ensembled neural networks.
csinva/stable-interpretation
Exploring ways to extract stable interpretations from neural networks.
csinva/imodels-alphaevolve
csinva/clinical-rule-development
Building and vetting clinical decision rules.
csinva/imodels-data
Preprocessed data for various popular tabular datasets to go along with imodels.