Join us
Help us answer the question
We're a small lab working across multimodal machine learning, computational neuroscience and video systems. There are no formal job listings yet. If your work fits one of the areas below, send us a few lines and a link to something you've made.
Research
- Multimodal machine learning
Video-language models: frame sampling, visual tokenization, temporal reasoning and the interpretability of their internal representations.
- Computational neuroscience
Voxel-wise encoding models, representational similarity analysis, and fMRI or EEG analysis of naturalistic video stimuli.
Engineering
- Video infrastructure
Decoding, frame extraction and re-encoding pipelines that scale from single clips to large stimulus datasets.
Collaborations
- Academic labs and teams
Groups with naturalistic-viewing neuroimaging data, or video-model questions that neural data could help answer.