Anish Mudide

I'm a sophomore at MIT studying Mathematics and Computer Science. My research focuses on figuring out how deep neural networks work.

I attended the MATS Program and am fortunate to collaborate with Max Tegmark.

Email  /  Scholar  /  Twitter  /  GitHub

profile photo

Publications

Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schroeder de Witt
Under review, 2024
arXiv / code

Opening the AI black box: program synthesis via mechanistic interpretability
Eric J. Michaud*, Isaac Liao*, Vedang Lad*, Ziming Liu*, Anish Mudide et al.
Under review, 2024
paper / code

DafnyBench: A Benchmark for Formal Software Verification
Chloe Loughridge, Qinyi Sun, Seth Ahrenbach, [...], Anish Mudide et al.
NeurIPS Math-AI Workshop, 2024
arXiv / code

Causal gene regulatory analysis with RNA velocity reveals an interplay between slow and fast transcription factors
Rohit Singh*, Alexander Wu*, Anish Mudide*, Bonnie Berger
Cell Systems, 2024
project page / video / arXiv / code

The contribution of historical processes to contemporary extinction risk in placental mammals
Aryn P. Wilder, Megan A. Supple, Ayshwarya Subramanian, Anish Mudide et al.
Science, 2023
paper / code

Generation of LexA enhancer-trap lines in Drosophila by an international scholastic network
Ella S. Kim, Arjun Rajan, Kathleen Chang, [...], Anish Mudide et al.
G3: Genes, Genomes, Genetics, 2023
paper / arXiv

SARS-CoV-2 drug discovery based on intrinsically disordered regions
Anish Mudide, Gil Alterovitz
PSB, 2021
paper / code

How much does the (social) environment matter? Using artificial intelligence to predict COVID-19 outcomes with socio-demographic data
Christos Makridis, Anish Mudide, Gil Alterovitz
PSB, 2021 (Oral Presentation)
paper / code


Replicated from Jon Barron.