Computation and Neural Systems PhD student @Caltech | Brain Computer Interfaces, Neural Signal Decoding | https://xitter.cf/t.co/438WcGkN1l
Joined November 2020
- Tweets89
- Following409
- Followers335
- Likes553
Want pretrained biosignal models that generalize to unseen channel layouts? Rethinking how we assign channel embeddings may help!
Presenting Device Passport #ICML2026 SD4Health
📍Saturday, July 11, 9:50am KT -- Hall A. More info⬇️
Learn more about Device Passport:
📍 Poster: Saturday, July 11, 2026, 9:50am KT -- Hall A
📄 arXiv: arxiv.org/pdf/2607.00249
🗓️ SD4Health Workshop: structureddata4health.github…
Special thanks to Chris Sandino and the team at Apple for the close collaboration, feedbacks, and ideas!
Geeling Chau retweeted
Excited to lead the AI Core of the Raynor Cerebellum Project @RaynorProject. Our team is developing AI models to move neuromodulation for cerebellar disorders from trial-and-error toward intelligent neurotechnology.
Grateful to collaborate with @yisongyue on this.
Story⬇️
Geeling Chau retweeted
Congratulations to @YuanSui123 & @GeelingC for rocking out at the @evermind Genesis competition! 🚀
We are building some amazing AI Agents for Science tech at @caltech.
@YueLabCaltech going strong! 💪
Full house at the Computer History Museum today. Great speakers, AI enthusiasts, and people who truly care about memories, all under one roof.
We shared our thoughts on:
• Memory and why it matters
• The future of memory infrastructure
• The future of the memory OS
This was also the grand finale of our Genesis 2026 competition. The quality of the projects, the presentations, and the sheer volume of code submitted truly blew us away.
It is clear that this community is pushing the boundaries of what memory infrastructure can be.
More to come. Stay tuned.
Geeling Chau retweeted
Excited to share our new work on cross-brain transfer of speech and handwriting BCIs! Some studies have required 10+ days of training data for peak BCI performance. Can pooling neural data from other users speed things up? 1/6
biorxiv.org/content/10.64898…
Geeling Chau retweeted
Ecstatic to announce Merge Labs! 🧠🚀
I’m honored to work alongside my co-founders—Tyson Aflalo, @mikhailshapiro, @sandroherbig, @alexblania, and @sama on bridging biological and artificial intelligence. They’re *the* team to take on a mission this ambitious.
We’re grateful to have partners like @OpenAI who share a long-term view on what it takes to build foundational technology.
If you want to work on hard, foundational neurotech problems, come build with us.
Geeling Chau retweeted
A team of scientists led by Caltech and Cedars-Sinai has developed a new artificial intelligence framework that can accurately, quickly, and efficiently create virtual models of brain neurons.
caltech.edu/about/news/model…
I'll be at #NeurIPS2025 presenting w/:
1️⃣ Eshani Patel and @yisongyue on generalizing models to input preprocessing
2️⃣ Chris Sandino et al., on new temporal reps of EEG
3️⃣ @shivashriganesh et al., on new iEEG training frameworks
📍Brain & Body FM on Sat
😍 🧠? Let's chat!! 🔗⬇️
NeurIPS 2025 Paper links:
1️⃣ arxiv.org/abs/2511.13022
2️⃣ arxiv.org/abs/2511.11940
3️⃣ openreview.net/forum?id=CdP8…
If you're excited about how scaling models can help enable robust and generalizable wearable and neuro technology, let's connect + chat!! 🧠🦾
Geeling Chau retweeted
Most of @YueLabCaltech will be at #NeurIPS2025!
Check out papers by the group & collaborators spanning:
🔬 AI for Science — closing the loop from experiment design to inverse problems
🎯 End-to-end conformal risk control
🌊 New diffusion methods with theoretical guarantees
🤖 Advances in LLM reasoning & formal verification
We're also developing a unified framework for scientific inverse problems — using foundation models to go from raw telescope/microscope/sensor data → scientific insights. Key results:
-- Reconstructed M87 black hole from real EHT data (led by @klbouman)
-- Plug-and-play priors + forward models across many domains
- Latest release is InverseBench :
devzhk.github.io/InverseBenc…
(w/ @Hongkai_Zheng, @BingliangZhang, @WendaChu32619, @ZihuiRayWu, @zross_)
Same algorithms also work for steering protein generative models with wet lab experimental data:
github.com/jsunn-y/SGPO
(w/ @jsunn_y, @WendaChu32619, @danielpkhalil, @francesarnold)
Many talented students graduating soon and exploring next opportunities! Come chat at our posters 👇
Geeling Chau retweeted
Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025!🧠
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 👉 brainbodyfm-workshop.github.…
Geeling Chau retweeted
We're excited to announce the Brain-to-Text '25 competition, with a new intracortical speech neuroscience dataset and $9,000 in prizes generously provided by @BlackrockNeuro_!. Can you do better than us at decoding speech-related neural activity into text?
kaggle.com/competitions/brai…
Geeling Chau retweeted
With over 500 delegates in attendance, the BCI Meeting was a tremendous success. A heartfelt thank you to all of you for the engaging discussions, meaningful exchanges, and the great energy throughout the event.
Geeling Chau retweeted
Our brain-to-voice synthesis brain-computer interface paper was published in @Nature today! This neuroprosthesis synthesized the voice of a man with ALS instantaneously, enabling him to ‘speak’ flexibly and modulate the prosody of his BCI-voice. 1/7
Paper: rdcu.be/eqH3C
Geeling Chau retweeted
📢 Heads-up to the neuro-ML/BCI community that we'll launch the Brain-to-Text '25 competition in ~a month, and it'll run through Dec. 31.
More intracortical electrodes! More varied utterances! More... speechy?
Rumor even has it there'll be cash prizes this year
Stay tuned...
Excited to share our new report on lessons learned from the Brain-to-Text '24 competition! arxiv.org/abs/2412.17227 The biggest jump in accuracy came from using a fine-tuned merger LLM to combine hypotheses from an ensemble (see figure).
In #Banff for the @BCISociety #BCI2025 meeting!
How can Machine Learning benefit BCIs?
🤝Would love to meet! (DM me)
📍Poster: Jun 4 (Wed) 4-6pm. P2-G-68
🗣Talk: Jun 5 (Thurs) Morning. W21: Large neural data models for BCIs. Organized by @_JoelYe🙌
Geeling Chau retweeted
Please share/amplify!
Apply now: forestneurotech.org/jobs
📍 Location: Bay Area, CA
Geeling Chau retweeted
I'm excited to share our latest work — "Data Heterogeneity Limits the Scaling Effect of Pretraining in Neural Data Transformers", where we examined the effect of scaling up pretraining data in neural foundation models carefully.🧐 (1/9)
Preprint: biorxiv.org/content/10.1101/…
