🚨 BREAKING NEWS 🚨 TREX workshop is back to IEEE VIS for the 3rd time!! (pls RT) ❓: human-centered considerations for AI-fused visualization, i.e., trust, cognitive biases, domain expertise, transparency, and human-in-the-loop!! ⏰ Submit by July 16 ℹ️: trexvis.github.io/Workshop2022/

Roslingifier, in the spirit of @charles_perin, Pierre Dragicevic, and @jdfaviz's Bertifier (aviz.fr/bertifier), provides automatic storytelling for animated scatterplots. In fact, the tool mimics Rosling's famous TED 2006 talk on global health: ted.com/talks/hans_ros… 2/

We achieve this in three ways: 1) natural language narrative; 2) visual effects for highlighting; and 3) temporal branching. The storylines, akin to a video editor timeline, is automatically generated and can then be edited by the user for clarity and effect. 3/

The author team includes Minjeong Shin, Joohee Kim, Yunha Han, lexing xie, @mtchl, Bum Chul Kwon | 권범철 | @[email protected], Sungahn Ko, and I (apologies for any Twitter handles I missed), and the paper is currently available as a TVCG preprint here: computer.org/csdl/journal/t… 4/

Additional resources as follows: DOI: 10.1109/TVCG.2022.3146329 Video: youtu.be/BTkwk00gU0g PDF: users.umiacs.umd.edu/~elm/projects/… We hope to present this paper at #ieeevis this October. See you there! 5/end

NLVIZ is back as a half-day workshop IEEE VIS 2022 focusing on research at the intersection of natural language and data visualization! ℹ️Learn more: nlvizworkshop2022.com Organizers: Vidya Setlur, Arjun Srinivasan (1/2)

Excited to see YouTube begin to open itself to outside researchers. Any step in this direction needs to be celebrated and encouraged. research.youtube

Thanks everyone for waiting patiently! #iclr2023 Call for paper for ICLR 2023 is out! Full paper deadline: Sept 28 iclr.cc/Conferences/20…

Lightning and Thunder: The Early Days of Interactive Information Visualization at the University of Maryland Written with @cplaisant July-Aug. 2022, IEEE Computer Graphics & Applications HCIL @iSchoolUMD UMIACS UMD Department of Computer Science computer.org/csdl/magazine/…

Join this year's town hall, via Zoom, on Monday, 1 August at 10:00 AM EDT to meet and hear from your 2023 #IEEECS presidential candidates. More Information @ bit.ly/3NRWQug

Just realized that I now have 40 (!) twitter threads! 🤩 I organized them into "Awesome Tips": github.com/jbhuang0604/aw… Really appreciate for all your comments, critics, likes, and retweets. Hope these threads are useful! What should I write next? 🤔

AI journalism has a hype problem. To move past the cycle of reacting to each story, Sayash Kapoor and I analyzed over 50 pieces from 5 prominent outlets. We've compiled a list of recurring pitfalls that readers should watch out for and journalists should avoid. aisnakeoil.substack.com/p/eighteen-pit…

MiniGPT-4 is literally just built based on our #BLIP2 with the latest LM #Vicuna, and it was using our LAVIS library, one of the most comprehensive open-source libraries for multimodal language-and-vision intelligence. github.com/salesforce/LAV…

Last month was particularly exciting for open-source AI, featuring several open source implementations of large language models (LLMs). Now we are seeing a big wave of open-source datasets! We had Databricks Dolly 15k and OpenAssistant Conversations for instruction finetuning.

It’s Friday, it’s the last day of #ieeevis, and we’re now getting ready for our paper on “Visualization Thumbnails”🎞️🌆🌁🌃 by authors Hwiyeon Kim, Joohee Kim, Yunha Han, Hwajung Hong, Oh-Sang Kwon, Young-Woo Park, myself, Sungahn Ko, and Bum Chul Kwon | 권범철 | @[email protected]. Room 109! […]