Hope to see you all at Valencia! Yassir Jedra and I will be presenting at Poster Session 2! (Auditorium 1 Foyer 58)

I'm really happy to be part of this team and be part of this workshop. #In2Writing workshop at #CHI2023 is amazing. katy ilonka gero Thiemo W. Dongyeop Kang (DK) Vipul Raheja Mina Lee Minsuk Chang John Joon Young Chung Kenneth Huang

Modern Transformer expressivity + throwback word2vec interpretability. Backpack's emergent capabilities come from making the model less expressive (not more), creating bottlenecks that force the model to do something interesting.

📢 I am thrilled to announce my new journey as a Research Scientist at Bell Labs (Cambridge, UK) led by Fahim Kawsar! I'll focus on On-Device & Edge AI systems research with incredible collaborators. Let's push the boundaries together!

📜I'm excited to announce that our research on performance estimation following personalization has been accepted to IMWUT and will be showcased at #UbiComp2023! 🎉 UbiComp Check out our paper here: arxiv.org/abs/2111.11053 📄

Excited to share the latest edition of our explainable AI (#XAI) course which focuses on a whole gamut of topics ranging from interpreting simple predictors to understanding the behavior of AlphaZero, LLMs, and diffusion models. Course Webpage: tinyurl.com/2dutdsxz (includes

Two #UIST2023 papers on interactive learning support systems/tools: Storyfier: Exploring Vocabulary Learning Support with Text Generation Models CriTrainer: An Adaptive Training Tool for Critical Paper Reading Check the camera-ready PDFs here🧐: zhenhuipeng.com

📢 Looking for current research on #HCI + #AI? Here's a collection of #UIST2023 preprints. I've collected them via arXiv, twitter and mastodon. Suggestions welcome! dbuschek.medium.com/uist23-preprin…

Excited to announce that our research on robust test-time adaptation for noisy streams has been accepted at #NeurIPS2023! Huge thanks to my incredible collaborators: Yewon Kim, Taeckyung Lee, Sorn Chottananurak, and Sung-Ju Lee. 🙌 Stay tuned for the code and camera-ready version!

🗣️Join me for my IMWUT (UbiComp) paper presentation tomorrow (Wed.) from 2 pm in Cozumel B! 📄 Title: "DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing" #IMWUT #UbiComp #UbiComp2023

📄Join me for my #NeurIPS2023 poster presentation tomorrow! "SoTTA: Robust Test-Time Adaptation on Noisy Data Streams" 📆 When: Tue 12 Dec 10:45 am- 12:45 pm 📍 Where: Great Hall & Hall B1+B2 (level 1) # 1707 NeurIPS Conference #NeurIPS #NeurIPS23 #MachineLearning #AI #TTA

Developed a cheat sheet for choosing the right statistical significance test and corresponding effect size measures in #HCI research: theiilab.com/notes/Hypothes…. Please always report effect size alongside any statistically significant findings. #Statistics #ResearchTools #chi2024

Awesome text-to-{music,sound} system from FAIR. And yes, it's open source.

🤔As an English second-language learner, I usually have trouble replacing a word, that I frequently used in my essays, with substitutes that show better language proficiency. ✍️Introducing ProLex: a benchmark for language proficiency-oriented lexical substitution 🧵(1/n)

Image-to-Music AI demo is insane 🤯 Drag an image get a generative soundtrack, still in shock at how well it works!

I am really excited to reveal what Google DeepMind's Open Endedness Team has been up to 🚀. We introduce Genie 🧞, a foundation world model trained exclusively from Internet videos that can generate an endless variety of action-controllable 2D worlds given image prompts.

📢 Looking for current research on #HCI + #AI? Here's a collection of 100+ #CHI2024 preprints, collected via arXiv and twitter. Suggestions welcome! dbuschek.medium.com/chi24-preprint…

I love music most when it’s live, in the moment, and expressing something personal. This is why I’m psyched about the new “DJ mode” we developed for MusicFX: aitestkitchen.withgoogle.com/tools/music-fx… It’s an infinite AI jam that you control 🎛️. Try mixing your unique 🌀 of instruments, genres,

A Design Space for Intelligent and Interactive Writing Assistants #CHI2024 👩🏻✏️🤖 What writing assistants do you use? What else are out there and how do they differ? What do we need to consider when designing new writing assistants? 🔗 arxiv.org/abs/2403.14117 (1/6)

If sperm whales could talk, what would they say? New research on their communication reveals a complex combinatorial system that challenges our understanding of animal vocalizations. By analyzing 8,719 whale click sounds called “codas”, using machine learning, MIT CSAIL &