Raymond Fok

We are looking for CS researchers to participate in a study exploring how AI can change the way we do literature reviews. 📚🧑‍🎓 Time: ~90 min, remote Compensation: $60 USD Sign up here: forms.gle/Pzw6YUhVUaZsS6… @dsweld @amyxzh @josephcc @marissa_rad @Siangliulue @turingmusician

We're seeking CS researchers to participate in a study on working with AI tools to come up with research project ideas! Recruitment survey: forms.gle/PPEW7coVVPHDdA… Compensation: $50 Amazon gift card Time: 90 mins @dsweld @Hoper_Tom @its_sshahid @Siangliulue @rayrayfok

We took our most efficient model and made an open-source iOS app📱but why? As phones get faster, more AI will happen on device. With OLMoE, researchers, developers, and users can get a feel for this future: fully private LLMs, available anytime. Learn more from @soldni👇

@adigunturu Thank you, and congrats on your best paper!

@rayrayfok I really liked your talk today very cool!

What if paper abstracts weren’t just static summaries? In our #UIST2024 paper, we present Qlarify, a mixed-initiative system built on a lightweight interaction technique that expands abstracts with details from the full text—empowering scholars to dive deeper, faster.

Check out our paper here: dl.acm.org/doi/abs/10.114… This work was done last summer with amazing collaborators at semantic scholar / ai2: @josephcc @tal_august @amyxzh @dsweld And come chat with us during the “Learning to Learn” session at 3:35pm on Weds 10/16!

Hello! We will be presenting our poster on 📃 scientific decontextualization🎓 at #EMNLP2023 TODAY (12/9) at 11am in the east foyer! This is work with @soldni, @rayrayfok @armancohan, and @kylelostat, conducted at @SemanticScholar/@allen_ai

Now that #UIST2023 is almost over and you are looking for new project ideas: Check out The Semantic Reader Open Research Platform that enables you to build interactive intelligent paper readers like Papeo and Synergi that we presented at the conference! openreader.semanticscholar.org

Excited by a new paper with @rayrayfok, arguing that AI explanations are rarely useful for supporting HAI decision-making. To be useful, expls need to help the human verify answer correctness (rather than show the AI’s thought process), but most don't! arxiv.org/pdf/2305.07722…

@jwnichls We’re in the process of improving the quality of generated highlights, but hope to release it soon along with a conference publication. And potentially incorporate some of the ideas into S2’s Reader

@rayrayfok @drewmikehead @turingmusician @kylelostat @MartiHearst @dsweld Is there somewhere I can try it out? If not, what are the barriers to releasing it?

Can intelligent tools help researchers skim papers? We developed Scim, an augmented reading interface with faceted highlights that scaffold information discovery during skimming. With @drewmikehead @turingmusician @kylelostat @martihearst & @dsweld. See arxiv.org/abs/2205.04561.