Fumeng Yang
LightNews LightNews
banner
fumeng.bsky.social
Fumeng Yang
@fumeng.bsky.social
430 followers 80 following 7 posts
Assistant Professor @ UMD CS┃she/her┃HCI, Vis, & daydreaming┃Prev Northwestern CS, Brown CS, Tufts CS ┃www.fmyang.com ┃fig-x.github.io
Posts Replies Media Videos
Reposted by Fumeng Yang
johnguerra.bsky.social
My #IEEEVIS 2025 paper explorer is live! 🎉
👉 johnguerra.co/viz/ieeevis2... 👈

An interactive #dataviz to explore 300+ papers by similarity. Perfect for:
✨ Discovering papers related to your interests
✨ Planning which sessions to attend
✨ Creating your own paper list (new!)

Pls help me distribute it
November 2, 2025 at 1:28 PM
fumeng.bsky.social
Please wake up early on Fri 😀
viewlab.bsky.social VIEW Lab @viewlab.bsky.social · Oct 14
A limitless source of #dataviz questions?
📜 Yuan Cui, Lily Ge, Yiren Ding, @fumeng.bsky.social @mjskay.com @laneh.bsky.social
evaluate the use of LLMs for generating visualization questions, e.g. for literacy assessments.
📍Catch our talk on Fri, Oct. 18 at 0900a
#IEEEVIS
osf.io/preprints/os...
Paper abstract. It reads: Visualization items—factual questions about visualizations that ask viewers to accomplish visualization tasks—are regu-larly used in the field of information visualization as educational and evaluative materials. For example, researchers of visualizationliteracy require large, diverse banks of items to conduct studies where the same skill is measured repeatedly on the same participants.Yet, generating a large number of high-quality, diverse items requires significant time and expertise. To address the critical need for alarge number of diverse visualization items in education and research, this paper investigates the potential for large language models(LLMs) to automate the generation of multiple-choice visualization items. Through an iterative design process, we develop theVILA(VisualizationItems Generated by LargeLAnguage Models) pipeline, for efficiently generating visualization items that measure peo-ple’s ability to accomplish visualization tasks. We use the VILA pipeline to generate 1,404 candidate items across 12 chart types and13 visualization tasks. In collaboration with 11 visualization experts, we develop an evaluation rulebook which we then use to rate thequality of all candidate items. The result is theVILAbank of∼1,100 items. From this evaluation, we also identify and classify currentlimitations of theVILApipeline, and discuss the role of human oversight in ensuring quality. In addition, we demonstrate an applicationof our work by creating a visualization literacy test,VILA-VLAT, which measures people’s ability to complete a diverse set of tasks onvarious types of visualizations; comparing it to the existingVLAT, VILA-VLAT shows moderate to high convergent validity (R= 0.70).Lastly, we discuss the application areas of theVILApipeline and theVILAbank and provide practical recommendations for their use.All supplemental materials are available athttps://osf.io/ysrhq/
October 15, 2024 at 11:47 PM
fumeng.bsky.social
Today I'm starting as an Assistant Professor at
UMD CS! I'm seeking PhD students to join my lab for Fall 25. Check out my new lab website for more details: fig-x.github.io. I also welcome connections with students and colleagues interested in collaborations! 🐢
August 1, 2024 at 6:24 PM