Hudson Golino
@GolinoHudson
Associate Professor of Quantitative Methods at the Department of Psychology - University of Virginia. NLP/LLMs, Network Science, Info Theory, Psychometrics.
How much faster is my G-AI Desktop Studio compared to ChatGPT (4o) to summarize a research paper? Check the video below! Spoiler: It's much faster!
Wow!!!!!!!
Can we hear what's inside your head? 🧠→🎶 Our new paper in @PLOSBiology, led by Jong-Yun Park, presents an AI-based method to reconstruct arbitrary natural sounds directly from a person's brain activity measured with fMRI. doi.org/10.1371/journa…
Symposium led by @MigSorrel on bridging Psychometrics and AI, with @diegoiglesias_ ! Very cool new work, and possible collaborations in sight!
🚀 A New Paper from Nature Communications: Explosive neural networks via higher-order interactions in curved statistical manifolds Aguilera, Morales, Rosas, Shimazaki 🔗 nature.com/articles/s4146… This study introduces a curved neural network that: • Accelerates memory retrieval…
Very excited for this work! We trained an agent to audit models, and evaluated it using the same auditing game that human evaluators participated in (including yours truly). It wins ~40% of the time! For context, some human teams never solved it. Others took hours.
New Anthropic research: Building and evaluating alignment auditing agents. We developed three AI agents to autonomously complete alignment auditing tasks. In testing, our agents successfully uncovered hidden goals, built safety evaluations, and surfaced concerning behaviors.
At the European Association of Methodology's 2025 Conference in Tenerife, Spain, presenting our work part of the UVAi Vanguard Project, with some friends!
At the European Association of Methodology 2025 Conference in Tenerife, Spain. Without words...
Scenes from the International Meeting of the Psychometric Society, 2025!
At the International Meeting of the Psychometric Society (@pmetricsoc ) with Alex Christensen, Aleksandar Tomasevic (@atomasevic ), and Lara Russell-Lasalandra (@larafromUVA)!
Learn to use natural language processing (NLP) techniques & large language transformer models (#LLMs) for research applications. Join "Text Classification with Large Language Transformer Models in #Rstats" w/ @GolinoHudson on Aug. 5-8.
Our zoom broadcast had an intruder disrupting the talk, and sharing inadequate material online... I'm not sure I get pissed off by that or if I take it as a sign of prestige that someone tried to sabotage our scientific presentation hahah
If you would like to see our presentation, the zoom link is below: virginia.zoom.us/j/96789730199?… Meeting ID: 967 8973 0199 Passcode: 141943
If you would like to see our presentation, the zoom link is below: virginia.zoom.us/j/96789730199?… Meeting ID: 967 8973 0199 Passcode: 141943
Tomorrow, from 9 to 10:15 am at @pmetricsoc, join us for our symposium - Generative Psychometrics: Advancing Psychological Scale Development Through Large Language Models. Lara Russell-Lasalandra will (@larafromUVA) talk about AI-GENIE: A simulation study on the fully automatic…
Tomorrow, from 9 to 10:15 am at @pmetricsoc, join us for our symposium - Generative Psychometrics: Advancing Psychological Scale Development Through Large Language Models. Lara Russell-Lasalandra will (@larafromUVA) talk about AI-GENIE: A simulation study on the fully automatic…
Attending the International Meeting of the Psychometric Society this week in Minneapolis (@pmetricsoc). If you're also attending, let's chat!
*Into the land of automatic differentiation* Material is out! A short PhD course for the CS PhD in @SapienzaRoma covering basic and advanced topics in autodiff w/ slides, (rough) Notion notes, and two notebooks including a PyTorch-like implementation. 😅 sscardapane.it/teaching/phd-a…
Do you know how Prompting Engineering techniques like Few-Shot Prompting, Chain-of-Thoughts Prompting, Prompt Chaining, Instructional Prompting, Role and Persona Prompting, can improve the quality of the items (or text) you generate via Large Language Models? If not, come learn…
Do you know what Prompt Engineering is? How can it be used to improve your research? Can you use prompt-engineering techniques to generate better survey items, or to improve the quality of data you extract from a research paper? What about doing all that in R? Come learn with me…
The G-AI Desktop Studio app comes with a solid set of Prompt Engineering interactive examples (see video below). And, did I mention this app is ULTRAFAST?
My new G-AI Desktop Studio is a lightning fast app for LLM usage. You can chat with your own documents, interact with state-of-the-art free and open-source LLM models, and more. Also, it has an interactive prompt engineering guide that is top-notch!
You can now select up to 22 free LLM models, upload your document(s) and ask questions on my new Groq AI Desktop. In the example below, my new app is summarizing a scientific paper presenting the entropy fit indices (that I published in 2021) in seconds.