Kathy Garcia
@NeuroKathyG
Computational Cognitive Science PhD @JHUCogSci | BS @Stanford |
Excited to be presenting this paper at #ICLR2025 this week @iclr_conf! Come check our poster if you want to know more!! 🧠🤖 📆 Thur, Apr, 24 3:00-5:30 - Poster session 2 (#64) 📄 bit.ly/4jISKES
What shapes the topography of high-level visual cortex? Excited to share a new pre-print addressing this question with connectivity-constrained interactive topographic networks, titled "Retinotopic scaffolding of high-level vision", w/ Marlene Behrmann & David Plaut. 🧵 ↓ 1/n
Who is jetlagged and ready to ROCK!? #ICLR2025 Let's gooooo!!!! 😱😱💪💪
My lab at Northwestern is hiring! We have openings for a Project Coordinator, Research Assistant, MRI Data Analyst, and Postdoc for studies examining neuroinflammation and mental and physical health. Please RT and share!! Click here for more information: acnlnorthwestern.com/join-the-lab
Introducing GenEx: Turn any image into a 3D world adventure! 1️⃣ Create a fully explorable 360° world in 3D from just a single image! 2️⃣ Explore interactively or with GPT assistance. 3️⃣ Advance embodied AI with this imagined world! Check out our website: genex.world
🚨 Thrilled to share that Compositional Generalization Across Distributional Shifts with Sparse Tree Operations received a spotlight award at #NeurIPS2024! 🌟 I'll present a poster on Tuesday and give an invited lightning talk at the System 2 Reasoning Workshop on Sunday. 🧵👇
One of the highlights of the Fall semester for me is organizing our PhD application mentorship program!!🧑🎓 We offer SOP and general grad school advice, with the goal of supporting first-gen and URM scholars. Got questions? Sign up here: forms.gle/V1tsYLU7L4BezR…
Our kidney work being finally out, that means I get to share some of my favorite images 🤩 Starting off with the results of our deep learning segmentation. We can label 17 micro anatomical components of the fetal kidney on H&E images.
Accepted to @COLM_conf! 🎉 Instruction-tuning helps LLMs produce more human-like responses. Does it also make LLMs 🤖 more similar to the human language system 🧠? Thread🧵⬇️ Paper: arxiv.org/abs/2312.00575 w/ @SyrielleMontar1, @bkhmsi, mentored by @martin_schrimpf, @ABosselut
Instruction-tuning Aligns LLMs to the Human Brain paper page: huggingface.co/papers/2312.00… Instruction-tuning is a widely adopted method of finetuning that enables large language models (LLMs) to generate output that more closely resembles human responses to natural language…
📢 Kathy García is now presenting "Modeling Dynamic Social Vision Highlights Gaps Between Deep Learning and Humans" at the #LatinXinAI workshop at #ICML2024! 🌟🤖🧠
Don't miss our LatinX in AI Workshop at ICML! 🌟 It's just around the corner! Connect with our incredible keynote speakers and be a part of this empowering community. #LatinXinAI #ICML2024. buff.ly/4aFYWJM
Missed out on ICLR Re-Align? No fear - here is a 🧵 on our new work: "Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting" led by the fearless @NeuroTaha, with the inimitable @GretaTuckute 1/n
I had so much fun working on this with Colin, @michaelfbonner and @leylaisi, but most of all @NeuroKathyG. It was a joy to work so closely with someone during one of the final projects of my PhD and am delighted to see it out!
📢 Excited to announce our latest pre-print: “Modeling dynamic social vision highlights gaps between deep learning and humans”! 🌟 w/ @emaliemcmahon, Colin Conwell, @michaelfbonner, and @leylaisi🧵 #NeuroAI #CognitiveScience [1/7]