Mainak Deb

computer/human vision, Neuroscience phd student @GeorgiaTech

[Mainak Deb @MainakDeb19]

Unlike the brain, most ANNs lack any kind of organization of units🧠

In our paper (ICLR 2025) with @mayukh091 @apurvaratan, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵

https://t.co/JXU3NXQkLb

[Mainak Deb @MainakDeb19]

Making apps I wish existed, episode 1

Bluetooth signal strength in real-time for iOS

[Mainak Deb @MainakDeb19]

no wrestling with obscure AWS cli commands,

no massive figshare zip files,

zero pain fMRI dataset that takes <5 min to get running

pip install mosaic-dataset

[mayukh09 @mayukh091]

🧠Excited to share MOSAIC: a unified fMRI mega-dataset: 430k+ trials, 160k stimuli, 93 subjects (and more to come!) all in a single brain space

Enables massive scale for modeling the visual cortex with just 2 lines of code

https://t.co/RmGFcycuC1

🐍pip install mosaic-dataset

[Mainak Deb @MainakDeb19]

Don't burn up your retina for science,

https://t.co/AXyCojsezO
no bs dark-mode for papers, PDFs, and most websites.

free, no install/download required :)

[Paras Chopra @paraschopra]

What if different parts of a neural network were forced to learn different aspects of the input?

They start showing specialized regions like the brain

Listen to @MainakDeb19 talk about an architecture that got him an ICLR 2024 spotlight!

New talk from @lossfunk!

[mayukh09 @mayukh091]

My work got featured in @TEDAIVienna👀

AtMan (NeurIPS 2023) explains LLM outputs, telling you which part of the context was critical.

https://t.co/bewV5Kdh91

https://t.co/g9Vc7k2Q2z

[Mainak Deb @MainakDeb19]

@bryan_johnson no way

[Mainak Deb @MainakDeb19]

@wtergan @mayukh091 @apurvaratan thanks @wtergan

you can check the openreview version for the appendix -> https://t.co/bCBQd2GVtY

[Mainak Deb @MainakDeb19]

Unlike the brain, most ANNs lack any kind of organization of units🧠

In our paper (ICLR 2025) with @mayukh091 @apurvaratan, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵

https://t.co/JXU3NXQkLb

[Mainak Deb @MainakDeb19]

@OpenNetBattle @mayukh091 @apurvaratan Thanks @OpenNetBattle🫡

[Mainak Deb @MainakDeb19]

Checkpoints released on @huggingface🤗
check: https://t.co/JkGd8h5Qiz

[Mainak Deb @MainakDeb19]

🤠Thanks to @neuranna, @NeuroTaha, @alishdipani, and everyone at MurtyLab.

https://t.co/0hn4rAiHhp

[Mainak Deb @MainakDeb19]

👀 Read the full paper here: https://t.co/t7ACKwmq6s

[Mainak Deb @MainakDeb19]

Artificial neural networks can predict neural responses of the human brain (fMRI), however,

they are vulnerable to small-scale adversarial attacks imperceptible to humans 🤖🧠

In our study with @nikolasmcneal @apurvaratan accepted at Neurips 2024 Unireps workshop, we find 👇

[Mainak Deb @MainakDeb19]

👾Sparse model-to-brain mappings improve resistance to attacks.

[Apurva Ratan Murty @apurvaratan]

🚀At @NeurIPSConf tomorrow? Don't miss @nikolasmcneal and @MainakDeb19 's poster at the @unireps workshop on the adversarial sensitivity of vision encoding models of fMRI responses! A brief teaser about what they find.

[Mainak Deb @MainakDeb19]

I'll be joining @artflow_ai as an intern 🚀

@artflow_ai lets users generate visual content using #AI, exciting stuff! 🖌️🤖🎨

give it a try 👀 -> https://t.co/2JDUeM9pMP