Francisco Acosta
@hopfbifurcator
PhD candidate @UCSBPhysics @geometric_intel lab | geometry, dynamics, AI, brains | prev physics @MIT | AI Research Fellow @atmo_ai | co-organizer @neur_reps
Combining precise, AI-powered weather modeling with drone-based cloud seeding to help make it rain ☔️
NeurReps is back for a fourth edition! See you in San Diego to discuss the intersection of geometry, topology, representation learning, mechanistic interpretability, and neuroscience
Are you studying how structure shapes computation in the brain and in AI systems? 🧠 Come share your work in San Diego at NeurReps 2025! There is one month left until the submission deadline on August 22: neurreps.org/call-for-papers
Are you studying how structure shapes computation in the brain and in AI systems? 🧠 Come share your work in San Diego at NeurReps 2025! There is one month left until the submission deadline on August 22: neurreps.org/call-for-papers
First #ICML2025 conference proceeding (icml.cc/virtual/2025/p…)! We (Blake Bordelon, Jacob Zavatone-Veth, @CPehlevan) developed a simple model to better understand state representation learning dynamics in both artificial and biological intelligent systems! Comments appreciated!
@atmo_ai and @RainmakerCorp are forming a strategic alliance to deploy the most precise weather modification platform in the world. We look forward to setting a new global standard of excellence for Al-driven, drone-based precipitation enhancement with @ADoricko
Announcing @RainmakerCorp and @atmo_ai 's strategic alliance to transform weather modification with AI-powered precision cloud seeding. We're combining our radar-driven, drone-based cloud seeding with their ultra-precise AI meteorology to fight drought worldwide. 🧵
Announcing @RainmakerCorp and @atmo_ai 's strategic alliance to transform weather modification with AI-powered precision cloud seeding. We're combining our radar-driven, drone-based cloud seeding with their ultra-precise AI meteorology to fight drought worldwide. 🧵
**How can we tell if a video is AI generated?** 👉 new paper: arxiv.org/abs/2507.00583 As scientists, we want to know if video models actually learned the laws of physics 🌍 As users, we want to make sure that we can trust and know when something is real 🏛️
You're into neuroscience and AI? 🧠 🤖 You're working on the mathematics that drives biological and artificial neural networks? We want to hear from you! Submit to NeurReps 2025 at @NeurIPSConf! 📅 Deadline: Aug 22 📄 Two tracks: 9p proceedings & 4p extended abstracts
📢 Call for Papers: NeurReps 2025 ‼️‼️‼️ 🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks. Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages). Deadline: Aug 22, 2025. neurreps.org/call-for-papers
absolutely STACKED speaker list at NeurReps 2025!
big thanks to our incredible lineup of invited speakers: SueYeon Chung (@s_y_chung), Surya Ganguli (@SuryaGanguli), Max Tegmark (@tegmark), Katrin Franke (@kfrankelab), Bastian Rieck (@Pseudomanifold), and Razvan Pascanu!
🚨One of the coolest workshops in AI is back! NeurReps 2025 is calling for papers on symmetry, geometry & topology in neural networks 🧠📐 If your work bridges theory & structure — don’t miss this. 📅 Deadline: Aug 22
📢 Call for Papers: NeurReps 2025 ‼️‼️‼️ 🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks. Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages). Deadline: Aug 22, 2025. neurreps.org/call-for-papers
📢 Call for Papers: NeurReps 2025 ‼️‼️‼️ 🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks. Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages). Deadline: Aug 22, 2025. neurreps.org/call-for-papers
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
The era of artificial scientific intelligence is here. As algorithms generate discoveries at scale, what role remains for human scientists?🤔 Thanks @PLOSBiology for publishing my perspective @ai_ucsb @ucsbece @UCSBengineering @ucsantabarbara ! journals.plos.org/plosbiology/ar…
Super stoked to share my first first-author paper that introduces a hybrid architecture approach for real-time neural decoding. It's been a lot of work, but happy to showcase some very cool results!
New preprint! 🧠🤖 How do we build neural decoders that are: ⚡️ fast enough for real-time use 🎯 accurate across diverse tasks 🌍 generalizable to new sessions, subjects, and species? We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes! 🧵1/7
🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better? Introducing: 🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀 📝 arXiv: arxiv.org/abs/2505.15405 🧵 (1/6)
Discover our lab's research with the @Bowers_WBHI on building AI models of the maternal brain @neuromaternal !🤰🧠 Thanks, @UCSBengineering , for the feature! Read more:👇
Pregnancy & motherhood transform the brain in ways we're only beginning to understand🧠 We're uncovering these changes with @susanna_carmona @MagdaMartinezGa @emilyjacobs @hannahgrotz @kayaGjordan @neuromaternal thanks to @cziscience's generous support ! tinyurl.com/38jb7hm6
🚨 New preprint from the lab! Discover *fast* topological neural networks, that leverage higher order structures without the usual computational burden! By @martincar98 @gbg1441 @Coerulatus @ninamiolane @lev_telyatnikov
Absolutely proud of this work! Huge thanks to @gbg1441, @ninamiolane, @Coerulatus — and of course @martincar98, who drove the project, learned on the fly, and kept the enthusiasm high at every turn!
Interested in graph and topological deep learning?🍩 Join us this wednesday online for this exciting @neur_reps global seminar series!🌟
Interested in the cutting edge of graph theory and topology for GDL? Join us this Wednesday at 17:00 IDT (16:00 CET) for our seminar with Haggai Maron's lab in Technion to learn how we can push the limits of expressivity in graph and topological deep learning!
New NanoGPT training speed world record from the Enigma Project 🎉 (@AToliasLab, @naturecomputes, enigmaproject.ai) We improve the efficiency of gradient all_reduce. Short explainer of our method 👇 [1/6]
New NanoGPT training speed record: 3.28 FineWeb val loss in 2.990 minutes on 8xH100 Previous record: 3.014 minutes (1.44s slower) Changelog: Accelerated gradient all-reduce New record-holders: @KonstantinWille et al. of The Enigma project
Interested in the cutting edge of graph theory and topology for GDL? Join us this Wednesday at 17:00 IDT (16:00 CET) for our seminar with Haggai Maron's lab in Technion to learn how we can push the limits of expressivity in graph and topological deep learning!