Chandan Singh
@csinva.bsky.social
Seeking superhuman explanations.
Senior researcher at Microsoft Research, PhD from UC Berkeley, https://csinva.io/
Senior researcher at Microsoft Research, PhD from UC Berkeley, https://csinva.io/
This was a huge effort with a wonderful team:
@rjantonello.bsky.social (co-first), Suna Guo, Gavin Mischler, Jianfeng Gao, Nima Mesgarani, & @alexanderhuth.bsky.social Excited to see how folks use it!
@rjantonello.bsky.social (co-first), Suna Guo, Gavin Mischler, Jianfeng Gao, Nima Mesgarani, & @alexanderhuth.bsky.social Excited to see how folks use it!
August 14, 2025 at 2:06 PM
This was a huge effort with a wonderful team:
@rjantonello.bsky.social (co-first), Suna Guo, Gavin Mischler, Jianfeng Gao, Nima Mesgarani, & @alexanderhuth.bsky.social Excited to see how folks use it!
@rjantonello.bsky.social (co-first), Suna Guo, Gavin Mischler, Jianfeng Gao, Nima Mesgarani, & @alexanderhuth.bsky.social Excited to see how folks use it!
These maps largely agree with prior findings (from Neurosynth neurosynth.org) and new findings (from a follow-up fMRI experiment using generative causal testing
arxiv.org/abs/2410.00812), suggesting this method is an effective, *automated* way test new hypotheses!
arxiv.org/abs/2410.00812), suggesting this method is an effective, *automated* way test new hypotheses!
August 14, 2025 at 2:06 PM
These maps largely agree with prior findings (from Neurosynth neurosynth.org) and new findings (from a follow-up fMRI experiment using generative causal testing
arxiv.org/abs/2410.00812), suggesting this method is an effective, *automated* way test new hypotheses!
arxiv.org/abs/2410.00812), suggesting this method is an effective, *automated* way test new hypotheses!
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.
August 14, 2025 at 2:06 PM
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.
We scale up our prior method that builds interpretable embeddings by asking LLMs yes/no questions. We use bigger LLMs, more data, and stability selection to build a 35-question model that generalizes across subjects and modalities bsky.app/profile/csin...
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!
Drop me a message if you want to chat about interpretability/language neuroscience!
August 14, 2025 at 2:06 PM
We scale up our prior method that builds interpretable embeddings by asking LLMs yes/no questions. We use bigger LLMs, more data, and stability selection to build a 35-question model that generalizes across subjects and modalities bsky.app/profile/csin...