Yiren Liu

HCI PhD Student @ UIUC | Former: Research Scientist Intern @ Adobe Research; Research Intern @ Conviva | Human-AI Collaboration | Multi-Agent System

[Yun Huang, PhD @YunHuang_HCI]

Ever gotten lost in a large conference? me... constantly 😅
That's why I built https://t.co/ohSRyCr6DU — starting with CHI'26.
What it does:
📅 Build a conflict-free schedule in 3 clicks — auto-detects time overlaps across your papers, sessions, and topics you care about. Your schedule lives in your local browser only. No server. No tracking.
🐢 Meet Turtle, your personal scheduling agent. It finds the real gaps in your schedule and suggests: "You've got 30 minutes after this talk. Want to signal you're up for coffee?" One tap drops a pin on the floor map. No calendar invite. No LinkedIn DM. Visible only to people signed in with work or school accounts.
🔍 More agents to help you find collaborators and discover work from unexpected corners of the field.
These features I use all these features myself! 😃
🚀🚀🚀 Early launch is live now!

🔜Coming soon:
🪝 PapersClaw APIs — raise your own "claw fish" (OpenClaw #OpenClaw bots 🦞🦞) in the vast ocean of literature. Request access in the app, first come first served.
📱 Mobile-friendly version before conference day!

Huge thanks to ACM and the CHI'26 organizing committee for putting together such an exciting program! @acm_chi
#CHI2026 #HCI #SIGCHI

[Pao Siangliulue @Siangliulue]

Are you a researcher in CS or a CS-adjacent field curious about how an AI agent can help you with your research project? Want to try a new tool for your research support in a paid user study ($100, 2 hr)? Limited spot numbers. See details and sign up here: https://t.co/lAhe3zNUK1

[Yiren Liu @yirenl2]

(2/2) https://t.co/rqswabZLK3

[Yiren Liu @yirenl2]

(1/2) We'll have the pleasure of hosting Dr. Ziqi Zhang from UIUC CS for a talk at SALT Lab @YunHuang_HCI on "Hardware-Rooted Secure LLM System": TAOISM, a TEE‑based confidential framework for secure LLM deployment on heterogeneous devices.
Mon 2/9, 3 PM CST via Zoom, Link ↓:

[Tal August @tal_august]

Deadline for submission in just under 10 days! Reach out if you have any questions.

[Yiren Liu @yirenl2]

@researchtrendai @sangho_suh @Siangliulue @tal_august @YunHuang_HCI https://t.co/DgNFpO8Rgc

[Yiren Liu @yirenl2]

#CHI2026 #HCI #AI #MultiAgentSystems Ever wonder how DeepResearch-style AI agents can be redesigned to support critical thinking?
Check out our CHI '26 paper "Perspectra", that build your own expert panels, steer debates, branch into parallel explorations.
https://t.co/MgEjuRWkfq

[Yiren Liu @yirenl2]

🎤 Deep dive talk at @ResearchTrendAI: https://t.co/zedj5h58hf
Grateful to collaborate with Viraj Shah, @sangho_suh, @Siangliulue, @tal_august and @YunHuang_HCI; and thanks to https://t.co/kYfCPxsaXL for the platform!

[Tal August @tal_august]

What is future of reading? 📗

Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026!

We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.)

👇 Submit a 2-4 pg paper: https://t.co/Gf5jRcydUd

[Yaman Yu @YamanYu3]

🚀 Children are turning to AI for learning, friendship, and emotional support, but most AI moderation systems are still trained on adult data.

This mismatch matters. Children speak differently; their jokes, slang, and teasing follow their own patterns. They also face unique online risks that adults rarely experience, such as grooming through AI roleplay, emotional overreliance on AI companions, or inappropriate advice from AI about their relationships.

When AI doesn’t recognize these differences, it can flag harmless play while missing real danger which leaving young users unprotected in the moments that matter most.

💡 To address this, we present YouthSafe, the first youth-centric safety benchmark and safeguard model for large language models (LLMs).

✨ YAIR Benchmark — over 12,000 annotated chat snippets capturing 78 youth-specific risks, from subtle emotional manipulation to privacy and social harm.
✨ YouthSafe Model — trained on YAIR, it significantly outperforms state-of-the-art (SOTA) guardrail systems in detecting subtle, developmentally relevant risks.
🎓 I’ll be presenting this work at #CCS2025 in Taipei!
📅 Oct 16, 2025
🕐 13:30 – 15:00
📍 Room 101C
💬 Session: Security Usability & Measurement #6

🌐 Read the preprint here: https://t.co/IkN4Zk3dK2

🙏 Special thanks to my amazing collaborators @yirenl2 , Jacky Zhang, @YunHuang_HCI , and Yang Wang for their inspiring teamwork and insights!

#CCS2025 #AI #Safety #GenerativeAI #ChildSafety #AIethics #TrustworthyAI

[Yun Huang, PhD @YunHuang_HCI]

🎉 We developed the #ConSphere app to enhance the #Ubicomp25 experience!
💡 With #ConSphere’s Digital Ribbons, you can personalize your profile to show your interests:
👩‍🏫 Looking for PhD students
👨‍🎓 Searching for advisors
🤝 Exploring cross-domain collaborations
✨ You can also plan your sessions smartly with an LLM-supported assistant. Discover papers and add them to your schedule planner!

❤️Huge thanks to my PhD student Yiren Liu @yirenl2 and Prof. Xin Yi’s PhD student Shuning Zhang from Tsinghua University for leading the development of #ConSphere!
Let’s be better connected at @ubicomp! 💫

Shortly, we will also release #ConSphere for @ACM_CSCW 2025!
I look forward to meeting everyone in-person at the conferences soon. 🥂

[Adobe Research @AdobeResearch]

What makes an @AdobeResearch internship unique? Freedom to explore, support to succeed, and the chance to see your work reach millions of users. Meet six interns who pushed innovation forward this summer. https://t.co/E4IFQVQPzQ

[Yiren Liu @yirenl2]

@sangho_suh @allen_ai Congrats Sangho! All the best to you!

[Yiren Liu @yirenl2]

5/5 🙌 Huge thanks to co-authors Pranav Sharm, Mehul Oswal, @HaijunXia , @YunHuang_HCI

Talk to us about the idea, and DM for a demo link!

[Yiren Liu @yirenl2]

1/5 Check out #PersonaFlow – our #DIS2025 paper on a mind-map interface where LLMs role-play as customizable domain experts and co-create research questions with you in real time.

Paper ➡️ https://t.co/i7sC3wLlM9
Code ➡️ https://t.co/dvSqpHdzOH

[Yiren Liu @yirenl2]

4/5 We also discussed the potential concerns around confirmation and authority bias & collaborative fixation. 🌐

[Yiren Liu @yirenl2]

@zhangchaodesign Thank you Chao!

[Yiren Liu @yirenl2]

What wonderful news🎉! Super lucky and grateful to be part of such an exciting project!

[Yun Huang, PhD @YunHuang_HCI]

📢 Exciting update! We’ve received a Notice of Allowance for our patent application "18/627,097 | 24-0420-US: Efficient content extraction from unstructured dialog text" https://t.co/xbiEj9YUSV— a major step toward bringing our research into the real world! 🎉

Grateful to my doctoral student Yiren Liu for the incredible work — outstanding job, @yirenl2! 🙏

Huge thanks to @ILinnovations, the Illinois Proof-of-Concept Program, and @iSchoolUI for their research and computing support — this wouldn't be possible without you! #innovation #patents #researchimpact