Are you interested in capturing professionals' tacit knowledge—like implicit decisions—and reusing it in generative agents 🤖 to better support creative work 👨🏻‍🎨? 👉 I will present my thesis work at UIST25 Doctoral Symposium (Poster: Tue evening). See you in Busan! 🇰🇷 #UIST2025

Fairies are live on https://t.co/dAGY8BIosE 🧚 $25 DECEMBER ONLY

Starting today, you will be able to select Gemini 3 Pro as an experimental model in Figma Make It’s early, but we’re already seeing impressive results: → Generate 0→1 results with a broad variety of styles, layouts, and interactions → Accurately translate Figma designs into

🚨 We’re hiring interns on the Asta Team @allen_ai! Join us in building research assistants for science! 🔬🧬 You'll work on topics ranging from agentic models to human-AI interfaces, publish papers, and shape how AI supports research. 🔗 Apply at https://t.co/UuFupmlkdi!

I'm hiring a student researcher for next summer at the intersection of MARL x LLM. If you have a strong background and research experience in MARL algorithms, please apply and drop me an email (so that I know you've applied!) https://t.co/sikY6cgzju

introducing Krea Nodes. our most powerful tool to date; all Krea in one interface. comment to get early access 👇

We’re hiring research interns @AdobeResearch to build the future of GenAI tools for filmmaking. You’ll work closely with filmmakers to rapidly prototype new tools for video storytelling. If interested, DM/Email me and apply here:

fairies

Agents are joining us at work -- coding, writing, design. But how do they actually work, especially compared to humans? Their workflows tell a different story: They code everything, slow down human flows, and deliver low-quality work fast. Yet when teamed with humans, they shine

We’re studying how people build or run multi-agent AI workflows — from LangGraph to n8n to running multiple ChatGPT tabs in parallel. 30-min Zoom interview · 💰$50 CAD or equivalent If you’ve built multi-agent /run multiple AI tools in parallel, sign up:

Come check our poster at #COLM2025 tomorrow (Wed 4:30-6:30pm) on CUPID 🏹, which evaluates whether LLMs can reason about user's context-dependent and evolving preferences from prior multi-turn feedback (spoiler: they can't)

Will present a poster at #COLM2025 on post-training for language model diversification Wednesday 11am! Modifying Large Language Model Post-Training for Diverse Creative Writing: https://t.co/PGimgHDyXs

Meet Pencil. A new "Design Mode for Cursor"

I will be presenting StoryEnsemble as the last talk of the last session at #UIST2025! Sadly, @sangho_suh could not be here, but he still made wonderful slides to illustrate how StoryEnsemble supports exploration & iteration in design! If you are staying, come check it out!

You can check this DS paper and poster on my website :) https://t.co/Gn52uWYord

Are you heading to Busan? 🏄‍♀️🌴🇰🇷 I'll present our paper 🪷BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents at #UIST2025! 📍Oct 1 · 11:12–11:24 AM (Miami Room)

1/ 🌍 Do #LLMs really treat all languages equally when citing evidence? 📑 In our new work, we uncover linguistic nepotism: models often trade off citation quality for language preference 👇

What if a how-to video could become your personal task assistant -- that truly understands the task and adapts to your context? We present Vid2Coach, a system that transforms instructional videos into a wearable, camera-based assistant. 🎥✨🕶️ #UIST2025

🎓I officially defended my PhD! Huge thanks to my amazing advisor @juhokim and committee @eytanadar @aliceoh @tongshuangwu @seo_minjoon. This fall, I'm excited to join @UMichCSE as a postdoc with @QVeraLiao to continue my research in human-centered AI and cognitive alignment!💙

🚨 How can we enable exploration & iteration in the design process — across personas, problem statements, solution ideas, and scenarios? Our #UIST2025 paper tackles this with AI and propagation-based mechanisms ⤵️/⤴️. 🌐 https://t.co/jD2h8urLFE 🎥 https://t.co/fGQ3i22D8d 🧵👇