Kevin Lin

@KevinQHLin

multimodal x agent x next postdoc @UniofOxford visiting @Stanford phd @NUSingapore | ex @Meta @Microsoft

Oxford, England

qhlin.me

Joined August 2022

Replies Articles Media

Pinned
Kevin Lin
@KevinQHLin
Jun 16
can AI write engaging news that people can trust? introducing ✨Data2Story: a data journalist agent. give it raw data, it generate a verifiable, multimodal article. 🔍verifiable: every claim is evidence-grounded, traces back to data, code, or a cited source. 🔮multimodal: the
00:00
Kevin Lin
@KevinQHLin
Aug 6
machines encode language in 1D sequence. humans understand it visually; just as children learn language by seeing and interacting with.
Mirac Suzgun
@suzgunmirac
Aug 5
1/ Today, @james_y_zou, @pmphlt, @jurafsky, and I are releasing string2string Studio: an open-source, in-browser platform that brings alignment, comparison, search, and evaluation into one interactive, visual environment for strings and sequences. See: string2string.org
Kevin Lin
@KevinQHLin
Jul 31
one function of next gen AR glasses is reading paper📑
Kosta Derpanis (back home, Toronto ❤️)
@CSProfKGD
Jul 30
Final walk and read in Zürich.
Kevin Lin
@KevinQHLin
Jul 31
nice blog.
Aryan Jain
@aryanjn9
Jul 30
Article
Continual Learning In Computer Use
Over the last year, we’ve run trillions of tokens on some of the hardest computer-use tasks in insurance. Pulling policy documents means logging into a carrier portal, finding the right customer,...
Kevin Lin
@KevinQHLin
Jul 24
lovely demo video
Ziwei Liu
@liuziwei7
Jul 24
🍎Thinking with Video towards Law-Grounded Physical Intelligence🍎 🥧Apple-π🥧 is the first benchmark that asks video models to reason through explicit physical laws w/ an auditable test of physical intelligence - Project: 21yrm.github.io/Apple-PI-homep… - Code: github.com/21yrm/Apple-PI
00:00