Sign in

Chandan Singh

@csinva.bsky.social
716 followers 108 following 10 posts

Seeking superhuman explanations. Senior researcher at Microsoft Research, PhD from UC Berkeley, csinva.io

PostsRepliesMedia
Chandan Singh @csinva.bsky.social · 20/01/2026
Really excited about our new work, which makes building clinical prediction models way easier! AI agents do the grunt work of hypothesizing and validating EHR features, enabling easy auditing by clinicians Iterating yields sensible SOTA (fully interpretable!) models arxiv.org/abs/2601.09072
010 1
Chandan Singh @csinva.bsky.social · 14/08/2025
The model is small enough that we can visualize the whole thing. No feature importances or post-hoc summaries, just 35 questions and a map showing their linear weights for each brain voxel.
100 1
Chandan Singh @csinva.bsky.social · 14/08/2025
New paper: Ask 35 simple questions about sentences in a story and use the answers to predict brain responses. Interpretable, compact, & surprisingly high performance in both fMRI and ECoG. 🧵 biorxiv.org/content/10.1...
120 2
Chandan Singh @csinva.bsky.social · 07/12/2024
At NeurIPS this week, presenting our work on crafting *interpretable embeddings* by asking yes/no questions to black-box LLMs. Drop me a message if you want to chat about interpretability/language neuroscience!
070 7
Chandan Singh @csinva.bsky.social · 20/11/2024
Science faces an explainability crisis: ML models can predict many natural phenomena but can't explain them We tackle this issue in language neuroscience by using LLMs to generate *and validate* explanations with targeted follow-up experiments
020 2
Chandan Singh @csinva.bsky.social · 20/11/2024
Mechanistic interp has made cool findings but struggled to make them useful We show that "induction heads" found in LLMs can be reverse-engineered to yield accurate & interpretable next-word prediction models
010 1