foveal/peripheral vision simulator in a web browser

Foveated vision interface for deep vision models

AI agents running research on single-GPU nanochat training automatically

A platform for reproducible world model research and evaluation

Unified framework for robot learning built on NVIDIA Isaac Sim

OpenShell is the safe, private runtime for autonomous AI agents.

[Nature Machine Intelligence 2025] Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception

A PyTorch Implementation of "Recurrent Models of Visual Attention"

Source code for EyeRobot

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Do deep neural networks have visual illusions?

Hyperalignment(Haxby et al., 2011) tutorial

Code for the manim-generated scenes used in 3blue1brown videos

HellaSwag: Can a Machine _Really_ Finish Your Sentence?

Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning (CVPR2020)

official code repository for the paper "Dissecting Query-Key Interaction in Vision Transformers"

Evaluate computational models on their alignment to behavioral and neural measurements in the domain of language

Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting

onavg is a cortical surface template that was created based on high-quality structural scans of 1,031 brains from OpenNeuro

Rebuild the Stable Diffusion Model in a single python script. Tutorial for Harvard ML from Scratch Series

A few CLI tools to immersively, browse, read Arxiv paper, save to notion & zotero, chat with them and save the chat history

Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections (NeurIPS 2023)

Code to train and analyze multi-region data-constrained RNNs and perform Current-Based Decomposition (CURBD)

Official repository for the paper "Behavior measures are predicted by how information is encoded in an individual’s brain"

A toolbox for comparing brain maps

Learning low-shot object classification with explicit shape bias learned from point clouds

Contrastive Learning Through Time

Implementation of the connectome embedding framework