#CSCW2025 preprint alert!
Science communication is essential—yet often neglected. With TranSlider, we demonstrate how to design AI interfaces that personalize scientific texts while preserving user agency + privacy. (1/🧵)
📄: https://t.co/7tvEAGgWBy
🔗: https://t.co/fqO9MXaJwK
Inspired by @taewook_cs , I was surprised that I never actually looked into the question of what happens if AI revises a paper based on reviews from AI iteratively. Is there going to be a fixed point?
As a first step, I asked NeuriCo to try it out. It turns out the answer is No in its setup as we have a never-satisfied reviewer.
Excited to dig into this deeper!
we're hiring! for onsites we fly people to sweden until our US visas are done
you'll enjoy working with us if you always have work top of mind, enjoy rational product dicussions, and want to build/sell/market something amazing
reach out through a mutual or otherwise dms!
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
https://t.co/AFJZ5kH7Ku
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
Did you know #Midjourney has a Storytelling Lab? 📜
We’re a small team building expressive, approachable and controllable tools for AI-supported storytelling: Worldbuilding, games, creative writing, and more.
Find our works here https://t.co/jmk0kmDq6H 🥳
New pre-print out with Xingyu Li @Xingyu19980214 and Shunyu Yao @ShunyuYao12
🎨We introduce ORIBA, an LLM agent that helps original character (#OC) artists develop their characters through role-play conversations.
🥳What is OC (original character)? An OC is a fictional character that an artist creates themselves, not taken from any existing work.
🎨ORIBA helps artists imagine their OCs as vivid, emotionally rich characters. It supports storytelling and personality, not image generation.
🎨It chats as the character using reasoning steps like observation, reflection, and behavior.
Artists control the visual side and use ORIBA to expand character depth.
In our study with 14 OC artists, ORIBA helped:
✔ Strengthen emotional bonds with OCs
✔ Uncover new personality details
✔ Lead to new artworks—7 participants made OC art inspired by the conversations
🎨ORIBA shows how LLMs can support creativity in subtle, text-based ways.
Artists used it to explore dialogue, emotion, and world-building. It worked like a writing companion that respects artistic direction and style.
This was written in 2024, and I’m very happy to finally share it now.
Happy to chat if you want to learn more!
🔗 https://t.co/nxQIttxrKQ
#HCI #LLM #AIagent
#Midjourney Storytelling Lab launched an AI game engine called #Dramamancer 🥳
As author, you set key story beats for the AI narrator to improvise from. As player, you explore by typing what you want to do 🎮
Have a try here! https://t.co/281UWtKsbG
how to get into ai:
- choose between language models or image models
- build from scratch with chatgpt
- recursively ask chatgpt about anything you don't intuitively understand
- explain things back to find gaps in understanding
A note to PhD applicants trying to get in contact with me:
(1) email is best
(2) keep it short
(3) tell me what uniquely interests you (be specific!), rather than attempting to use words in my recent papers vacuously
I will join Northwestern University Computer Science as an Assistant Professor in Fall 2026!
I am actively recruiting PhD students and seeking collaborations in robotics, human-robot interaction, brain-computer interfaces, cognitive science, societal impact of AI & automation, and AI for art & design.
Please see the recruitment announcement on my personal website, and feel free to reach out!
Ryan Louie, Postdoctoral Fellow in Stanford NLP and HCI groups, will speak to us tomorrow 11/12 at our @Mila_Quebec HCAI seminar, 3-4pm EST, on "Adapting LLMs to Upskill Novices for High-Stakes Domains." Researchers are welcome to join remotely, just email me for the link.
🎓 PhD Recruitment | Texas A&M CS
I am seeking 1–2 PhD students for Fall 2026 in Human–AI Interaction, with a focus on AI for education.
✅ Motivated and responsible
✅ CS background
✅ Full-stack development or LLM fine-tuning experience is a plus
📅 Deadline: Dec 15, 2025
🧠⚙️ Interested in decision theory+cogsci meets AI? Want to create methods to rigorously design/evaluate human-AI workflows?
I'm recruiting PhDs to work on
🎯 Stat foundations of multiagent collab
🌫️ Uncertainty & meta-cognition
🔎 Interpretability
💬 LLMs in behavioral sci