Hi there π I'm Chandan, a Senior Researcher at Microsoft Research working on interpretable machine learning. Homepage / Twitter / Google Scholar / LinkedIn
Interpretable and accurate predictive modeling, sklearn-compatible (JOSS 2021). Contains FIGS (PNAS 2022) and HSTree (ICML 2022)
Interpretability for text. Contains Aug-imodels (Nature Communications 2023)
, Tree-Prompt (EMNLP 2023)
, iPrompt (ICLR workshop 2023)
, SASC (NeurIPS workshop 2023)
, and QA-Embs (NeurIPS 2024)
adaptive-wavelets Adaptive, interpretable wavelets (NeurIPS 2021)
Utilities for trustworthy data-science (JOSS 2021)
deep-explanation-penalization Penalizing neural-network explanations (ICML 2020)
hierarchical-dnn-interpretations Hierarchical interpretations for neural network predictions (ICLR 2019)
transformation-importance Feature importance for transformations (ICLR Workshop 2020)
automated-brain-explanations Building natural-language explanations for the brain. Contains GCT (arxiv 2024)
clinical-rule-development Building and vetting clinical decision rules, including vetting an intraabdominal rule (PLOS Digital Health 2022), analyzing patient perspectives for approving rules (Kornblith et al. 2025, Nature scientific reports), or analyzing bias across CDIs (Obra et al. 2025). See also general PECARN data preprocessing (clinical-rule-vetting
)
covid19-severity-prediction Extensive COVID-19 data + forecasting for counties and hospitals (HDSR 2021)
molecular-partner-prediction Predicting successful CME events using only clathrin markers
gan-vae-pretrained-pytorch Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch
gpt-paper-title-generator Generating paper titles with GPT-2
disentangled-attribution-curves Attribution curves for interpreting tree ensembles trees (arxiv 2019)
matching-with-gans Matching in GAN latent space for better bias benchmarking. (CVPR workshop 2021)
data-viz-utils Functions for easily making publication-quality figures with matplotlib
mdl-complexity Revisiting complexity and the bias-variance tradeoff (JMLR 2021)
pasta Post-hoc Attention Steering for LLMs (ICLR 2024), led by Qingru Zhang
meta-tree Learning a Decision Tree Algorithm with Transformers (TMLR 2024), led by Yufan Zhuang
sim-dino Simplifying DINO via coding rate regularization (arXiv 2025), led by Ziyang Wu
explanation-consistency-finetuning Consistent Natural-Language Explanations (COLING 2025), led by Yanda Chen
induction-gram Interpretable Language Modeling via Induction-head Ngram Models (arXiv 2024), led by Eunji Kim & Sriya Mantena
Major: autogluon , big-bench
, nl-augmenter
Minor: conference-acceptance-rates , iterative-random-forest
, interpretable-ml-book
, awesome-interpretable-machine-learning
, awesome-machine-learning-interpretability
, awesome-llm-interpretability
, executable-books
, deep-fMRI-dataset
hummingbird-tracking, imodels-experiments, cookiecutter-ml-research, nano-descriptions, news-title-bias, java-mini-games, imodels-data, news-balancer, arxiv-copier, dnn-experiments, max-activation-interpretation-pytorch, acronym-generator, hpa-interp, sensible-local-interpretations, global-sports-analysis, mouse-brain-decoding, ...