Fun! 🎉

Don’t forget to try our interactive widget on the project website. Test some of the encoding models in the paper and visualize brain predictivity right in your browser 🤗🧠

This project wouldn’t have happened without Ruimin Gao(@ruimingao.bsky.social) and Anya Ivanova(@neuranna.bsky.social)

A special thank you to Anya, my advisor, mentor, and constant source of encouragement. Your support means the world to me, and I’m so grateful to be learning from you

✨ Takeaway:

LITcoder lowers barriers to reproducible, comparable encoding models and provides infrastructure for methodological rigor.

We also highlight pitfalls & controls:
🚩 Shuffled folds inflate scores due to autocorrelation
✅ Contiguous + trimmed folds give realistic benchmarks
⚠️ Head motion reliably reduces predictivity

📊 Replicating past results

1️⃣ Language models outperform baselines, embeddings, and speech models in predicting the language network
2️⃣ Larger models yield higher predictivity
3️⃣ Downsampling and FIR choices substantially shape results

We showcase LITcoder on 3 story-listening fMRI datasets:

1️⃣ Narratives
2️⃣ Little Prince
3️⃣ LeBel

Comparing features, regions, and temporal modeling strategies.

🛑 Currently, we support language stimuli
But the framework is extensible to other modalities(Video coming soon!)

The library is composed of four main modules:

1️⃣ AssemblyGenerator
2️⃣ FeatureExtractor
3️⃣ Downsampler
4️⃣ Mapping

Why this matters:
Encoding models link AI representations to brain activity, but…

1. Pipelines are often ad hoc

2. Methodological choices vary

3. Results are hard to compare & reproduce

LITcoder fixes this with a general-purpose, modular backend.