Devon Stoliker
@dpsyc42
Motivated to understand and better the conditions of life @ CompNeuro Lab, Monash University. What survives is not us; what survives is the story of us.
Happy to share that our work applying precision mapping to individuals with depression sampled longitudinally over an extended period has been published this week in @nature. Brief recap of the main findings and their potential implications below. nature.com/articles/s4158…
Christmas came early! 🎅🏻 Today marks the newest release of the HuggingChat 🤗 update with some really exciting capabilities! First up, automatic context injection! 1) Open a file in a supported app, summon HFChat, and it pre-populates the context window. No more copy-pasting
How do you like your pie? 😋 Many UX and perf improvements planned but @Kveykva and I are cooking 😌
Our new paper shows #psilocybin has similar long-term antidepressant effects as the #SSRI escitalopram but leads to greater improvements in psychosocial functioning, connectedness, and life meaning. Published in Lancet @EClinMedicine. thelancet.com/journals/eclin… 🧵1/10
1/3 Let me unpack more. Deep neural network (DNN) harmonization can remove nonlinear, spatially-distributed site differences missed by ComBat. BUT DNNs also remove real biological info :( We prove that this issue is inherent to approaches that ignore covariate (e.g. age, sex)...
Backlog in announcing preprints, but here's goes! Preprint #3 by @anlijuncn doi.org/10.1101/2024.0… proposes DeepResBat, a deep learning alternative to ComBat that harmonizes MRI while accounting for covariates. We show large improvements over classical & deep learning baselines
We spent a lot of effort on making our open source version be excellent. We put together a new system of building metadata of arbitrary PDFs, full-text search, and more. See it here: github.com/Future-House/p… 4/
ok here's my full review of this paper. It's easy and short, you should just read it if you want to. arxiv.org/abs/2409.04109
Large Language Model Agents is the next frontier. Really excited to announce our Berkeley course on LLM Agents, also available for anyone to join as a MOOC, starting Sep 9 (Mon) 3pm PT! 📢 Sign up & join us: llmagents-learning.org
Introducing Project Sid: the first simulations of 1000+ truly autonomous agents collaborating in a virtual world, w/ emergent economy, culture, religion, and government Humans are the only species to land the moon, because we can cooperate at a vast scale Can AI do the same?