collaborators

6 papers

cs.LG2026

The Concept of Representation in ML: Beyond Plato and Aristotle

Gilad Landau, Aviv Keren

Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization. As models scale and their ca…

cs.LG2025

Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset

Gereon Elvers, Gilad Landau, Oiwi Parker Jones

Non-invasive brain-computer interfaces (BCIs) are beginning to benefit from large, public benchmarks. However, current benchmarks target relatively simple, foundational tasks like…

cs.LG2025

The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset

Gilad Landau, Miran Özdogan, Gereon Elvers +15

The advance of speech decoding from non-invasive brain data holds the potential for profound societal impact. Among its most promising applications is the restoration of communicat…

cs.LG2025

LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale

Miran Özdogan, Gilad Landau, Gereon Elvers +5

LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5 larger than the next comparable dataset and…

cs.LG2025

The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning

Dulhan Jayalath, Gilad Landau, Brendan Shillingford +2

The past few years have seen remarkable progress in the decoding of speech from brain activity, primarily driven by large single-subject datasets. However, due to individual variat…

cs.LG2025

Unlocking Non-Invasive Brain-to-Text

Dulhan Jayalath, Gilad Landau, Oiwi Parker Jones

Despite major advances in surgical brain-to-text (B2T), i.e. transcribing speech from invasive brain recordings, non-invasive alternatives have yet to surpass even chance on standa…