Ever feel lost in jargon while watching technical videos - and stuck trying to find clear, timely help? Check out our work at #CHI2025 on how real-time AI systems can bridge knowledge gaps without overwhelming users!

RT @JiayiiGeng: Using LLMs to build AI scientists is all the rage now (e.g., Google’s AI co-scientist [1] and Sakana’s Fully Automated Scie….

RT @owen_x_zhang: Working on my @ACM_CSCW paper 5 hours before the deadline and overleaf crashed?????

RT @cindy_x_wu: Introducing COMPACT: COMPositional Atomic-to-complex Visual Capability Tuning, a data-efficient approach to improve multimo….

@JordAckerman @manaswisaha Sadly, none of us will be in Japan — but we'll present online at the "Narratives and AI Support" session ( on Thursday, May 1, 9 AM!.Read the full paper 📷

This work was done when I was a summer intern at Accenture Labs, together with my awesome collaborators Aadit Shah @JordAckerman , and @manaswisaha.

We map out a design space for real-time knowledge support systems, and discuss design implications for 1) balancing automation vs user control 2) building trust in AI-generated info 3) personalizing knowledge support 4) generalizing jargon explanation to other knowledge support.

Findings? 📷.* No "one-size-fits-all" formats: user preference depends on context, word, and their habits and backgrounds. * Participants want a balance between user-initiated and automated support, along with personalization and just-in-time assistance.

We built StopGap, a prototype that explains jargon in videos in various knowledge representation formats (definitions, metaphors, lists, and images), and tested it out through a design probe study (N=24)

RT @JiahaoQiu99: Can AI Be Blamed for a Teen’s Suicide? Do AI Chatbots encourage suicide?.🧒📱What if your teen’s favorite AI character cross….

RT @itsraynez: 📢I'm recruiting PhD students for Fall 2025 as I begin my journey as an assistant professor at @NJIT in Jan 2025. Our lab aim….

RT @annamfang: 🎉"Exploring Trade-Offs for Online Mental Health Matching: Agent-Based Modeling Study" is published in JMIR! . 💻We show how a….

RT @acmsigcas: REMINDER! Understanding&Developing Decentralized Systems Yuhan Liu, Nov 22, 1pm EST. Food delivery platforms control commis….

RT @dcalacci: are you at #CSCW24 ?? are you NOT a phd student??? do you want to be?? if you want to do a weird phd that spans community res….

RT @XingjianZhang6: Social media challenge day 1!!.With first time UISTers @theryanliu and @yuhanliu_mika! They did their undergrad/master’….

RT @manoelribeiro: I am recruiting 1-2 PhD students for Fall 2025 at Princeton to work on Comp Social Science/Societal Impact of GenAI/GenA….

RT @PrincetonHCI: Social media challenge day2!!. @PrincetonHCI Group photo with UIST vet professors! @ACMUIST #UISTChallenge #UIST2024 . P….

RT @PrincetonHCI: Hello X! This is Owen @XingjianZhang6, the social media chair for Princeton HCI. I will be managing X social account for….

RT @jyangballin: SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-benc….

RT @theryanliu: Reasoning about how others will react to what you say is hard. What if we use LLMs to develop better intuitions? 😲. Introdu….