Uploaded February 2026 | Updated September 2026, 2 weeks ago
Apply to join Foresight Neurotech program:* foresight.org/focus-areas/neurotechnology
A group of neuroscience researchers, entrepreneurs, and allies advancing beneficial short-term and long-term neurotechnology applications.
*Richard Csaky | Scaling Next-Brain-Token Prediction*
Abstract: Modern AI has converged on a surprisingly general principle: learn powerful priors by predicting what comes next. In this talk, I argue that the same scaling-first recipe can be applied to brain recordings to move from task-specific decoders toward brain foundation models, specifically of the causal, generative kind. I’ll present a framework that treats high-bandwidth electrophysiology (with MEG as a motivating case) as a token stream: first, learn an efficient tokenizer that globally compresses spatiotemporal activity into discrete tokens; then, train a causal long-context sequence model with a standard next-token objective. Conditioning is implicit: instead of adding subject and task labels, or bespoke heads, a snippet of real brain activity becomes the “prompt,” and the model learns to continue it, encouraging specificity to session, subject, and context while remaining architecture-agnostic and compatible with frontier multimodal backbones. I’ll close by discussing what “on-manifold” long-horizon neural generation should mean, why evaluation must probe drift and prompt-specificity (not just reconstruction), and how brain tokens could ultimately be interleaved with language, vision, and action tokens as a route to grounding and more efficient reasoning.
Bio: Currently building large-scale foundational brain models as an independent researcher funded by the Foresight Institute. Previously, designed and built muscle-based gesture control applications at Sonera, a neurotech sensor startup. PhD in neuroAI from Oxford, and a long time ago (2017-2019) I was doing research in Transformer-based dialog models. I am interested in pursuing the development and integration of AGI into our lives in a way that fits into the natural human experience - as natural as a sword/hammer feels for physical augmentation. The only way to survive the above-human structures and technologies we are creating is to augment the mind to be able to deal with them.
══════════════════════════════════════
*About The Foresight Institute*
The Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1986 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support. From molecular nanotechnology, to brain-computer interfaces, space exploration, cryptocommerce, and AI, Foresight gathers leading minds to advance research and accelerate progress toward flourishing futures.
*We are entirely funded by your donations. If you enjoy what we do please consider donating through our donation page:* foresight.org/donate
*Visit* https://foresight.org, *subscribe to our channel for more videos or join us here:*
*• Twitter:* twitter.com/foresightinst
*• Facebook:* facebook.com/foresightinst
*• LinkedIn:* linkedin.com/company/foresight-institute
══════════════════════════════════════
*Timecodes*
00:00 Intro
00:32 Talk Overview
01:53 Why Brain Foundation Models
04:08 Why MEG & Next-Token Prediction
07:19 Model Recipe
10:47 Datasets & Preprocessing
13:46 Tokenizer Design
15:03 BrainTokMix Architecture
18:33 Tokenizer Quality Checks
21:36 Transformer Setup
28:03 Generation Evaluation
32:18 Results
37:56 Limitations & Future Work
40:40 Q&A Highlights
44:01 Closing
Apply to join Foresight Neurotech program:* foresight.org/focus-areas/neurotechnology
A group of neuroscience researchers, entrepreneurs, and allies advancing beneficial short-term and long-term neurotechnology applications.
*Richard Csaky | Scaling Next-Brain-Token Prediction*
Abstract: Modern AI has converged on a surprisingly general principle: learn powerful priors by predicting what comes next. In this talk, I argue that the same scaling-first recipe can be applied to brain recordings to move from task-specific decoders toward brain foundation models, specifically of the causal, generative kind. I’ll present a framework that treats high-bandwidth electrophysiology (with MEG as a motivating case) as a token stream: first, learn an efficient tokenizer that globally compresses spatiotemporal activity into discrete tokens; then, train a causal long-context sequence model with a standard next-token objective. Conditioning is implicit: instead of adding subject and task labels, or bespoke heads, a snippet of real brain activity becomes the “prompt,” and the model learns to continue it, encouraging specificity to session, subject, and context while remaining architecture-agnostic and compatible with frontier multimodal backbones. I’ll close by discussing what “on-manifold” long-horizon neural generation should mean, why evaluation must probe drift and prompt-specificity (not just reconstruction), and how brain tokens could ultimately be interleaved with language, vision, and action tokens as a route to grounding and more efficient reasoning.
Bio: Currently building large-scale foundational brain models as an independent researcher funded by the Foresight Institute. Previously, designed and built muscle-based gesture control applications at Sonera, a neurotech sensor startup. PhD in neuroAI from Oxford, and a long time ago (2017-2019) I was doing research in Transformer-based dialog models. I am interested in pursuing the development and integration of AGI into our lives in a way that fits into the natural human experience - as natural as a sword/hammer feels for physical augmentation. The only way to survive the above-human structures and technologies we are creating is to augment the mind to be able to deal with them.
══════════════════════════════════════
*About The Foresight Institute*
The Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1986 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support. From molecular nanotechnology, to brain-computer interfaces, space exploration, cryptocommerce, and AI, Foresight gathers leading minds to advance research and accelerate progress toward flourishing futures.
*We are entirely funded by your donations. If you enjoy what we do please consider donating through our donation page:* foresight.org/donate
*Visit* https://foresight.org, *subscribe to our channel for more videos or join us here:*
*• Twitter:* twitter.com/foresightinst
*• Facebook:* facebook.com/foresightinst
*• LinkedIn:* linkedin.com/company/foresight-institute
══════════════════════════════════════
*Timecodes*
00:00 Intro
00:32 Talk Overview
01:53 Why Brain Foundation Models
04:08 Why MEG & Next-Token Prediction
07:19 Model Recipe
10:47 Datasets & Preprocessing
13:46 Tokenizer Design
15:03 BrainTokMix Architecture
18:33 Tokenizer Quality Checks
21:36 Transformer Setup
28:03 Generation Evaluation
32:18 Results
37:56 Limitations & Future Work
40:40 Q&A Highlights
44:01 Closing
