Parker Jones Neural Processing Lab (PNPL)

community

https://pnpl.robots.ox.ac.uk/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

latentdulhan submitted a paper 1 day ago

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

oiwi updated a dataset 3 days ago

pnpl/MegNIST

latentdulhan submitted a paper 4 days ago

The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

View all activity

Papers

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

View all Papers

pnpl 's papers 5

Submitted by

Dulhan Jayalath

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Parker Jones Neural Processing Lab (PNPL)

Submitted by

Dulhan Jayalath

The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

Parker Jones Neural Processing Lab (PNPL)

Submitted by

Dulhan Jayalath

A Common Measure of Communication for Speech Brain-Computer Interfaces

Parker Jones Neural Processing Lab (PNPL)

3 2

Submitted by

Dulhan Jayalath

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

Parker Jones Neural Processing Lab (PNPL)

14 2

Submitted by

Dulhan Jayalath

MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training

Parker Jones Neural Processing Lab (PNPL)

17 3

AI & ML interests

Recent Activity

Papers

Team members 6

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

A Common Measure of Communication for Speech Brain-Computer Interfaces

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training