8 papers
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
Dulhan Jayalath, Oiwi Parker Jones
Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient generalisation by learn…
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Dulhan Jayalath, Shashwat Goel, Thomas Foster +5
Where do learning signals come from when there is no ground truth in post-training? We show that inference compute itself can serve as supervision. By generating parallel rollouts…
Training AI Co-Scientists Using Rubric Rewards
Shashwat Goel, Rishi Hazra, Dulhan Jayalath +8
AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the ability to generate a rese…
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs
Dulhan Jayalath, James Bradley Wendt, Nicholas Monath +2
Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tunin…
The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset
Gilad Landau, Miran Ãzdogan, 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…
LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
Miran Ãzdogan, 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…