👴✍🆕 📄
Apparently this is how users of Chinese social media tries to evade content moderation!!
Check out our new work exploring several cloaking techniques in social media that "cloaks" there hateful intentions!!
How does LLM understands them?
Do you feel like your AI anime characters are always out-of-character?
How do we evaluate this?
I am thrilled to introduce our work: InCharacter- a novel perspective to evaluate the personality fidelity of RPAs with psychological scales
I wanna take an gap year just to do research…
Don’t wanna study…
Imma never gonna get a PhD offer if I don’t do more research 😭😭😭
And also learn more fundamental Deep Learning
Chinese offensive language has been interesting topic to investigate in- due to the fact that Chinese is heavily dependent on context
We did a survey on what kind of stuff people did before and what needs to be done in the future.
Check this out.
I am happy to announce that the work has been accepted in ACL 2024 main conference.
The first author
@xintao_w
will be in ACL in person. Feel free to ask him questions if you have any
Thanks again for all the support from all the authors!
Do you feel like your AI anime characters are always out-of-character?
How do we evaluate this?
I am thrilled to introduce our work: InCharacter- a novel perspective to evaluate the personality fidelity of RPAs with psychological scales
Reflecting back, I can not thank enough for Prof.Roy
@SRoyLee
for providing me this amazing 2 months opportunity in SUTD
I have met so many brilliant people who have given me advice and inspired me.
I hope we keep in touch…even after I left
Time to move on!
I should be an liberal art student...
should learn something like history/philosophy instead of CS
and... my undergrad life is "almost over" doesnt seem like I can get more exposure to this :-(
Kinda proud of myself on this
My comp bio project on Transmembrane Helix detection on DeepTMHMM training set
Good job Algo
(Even though the state of Art is like 5% higher lmao)
🔆From Persona to Personalization: A Survey on Role-Playing Language Agents
🔍 Dive into our comprehensive survey of RPLA technologies, their applications, and the exciting potential for human-AI coexistence.
📖 Paper:
[1/3]
On behalf of arXiv CV dataset and evaluation committee, I'd like to announce that we will ask authors to discontinue the use of the Lena Forsén image.
Instead, we encourage the use of the image of Frieren eating a gigantic hamburger.
Thank you for your understanding.
@prajdabre1
It's kinda a desperate take- the field is developing so fast, the peers are competitive, spots are limited- even worse- my coursework is very loaded. It is known that we need ideas effort and resource to succeed in research and ideas is all i had (even that might be scooped)
Is there something in called computational literature?
Always wonder this- either the study of how we can generate literature through computational lens
Or we start analyzing what LLM implies when they write their work?
Look at who is here!!!
The very professor
@SRoyLee
himself!
Very happy to finally meeting him in person at Doha!
Looking forward to his talk on Monday!
@leonluleonlu
Welcome onboard my friend!
Amazing friend of mine in CMU-P. Does amazing research and have crazy in-semester schedule.
Guys should start following him- literally rising star
Ada olimpiade internasional baru, yaitu bidang AI (IOAI)
Rupanya Indonesia punya perwakilan, dibina dan diseleksi oleh
Penasaran proses seleksi dari Indonesia, sempat kontak tapi tidak dibalas
Mungkin bisa bantu2
ex-IOI, TOKI, tahu sedikit tentang AI
I want to revive
@sigfunsai
!
Guys we are recruiting
Please let me know if you are interested in some form of fun project in AI and let me know?
I have a discord group for “approved” people doing independent research on weird topics lol!
Not everyone has to opportunity to be able to work with a lab…
And when that happens long-term projects are not incentivized bcz your project can be easily scooped by big names…
Talking to grad students, too many think that long-term projects (not scattered papers), proper code releases, thoughtful benchmarks are "not incentivized".
Most often they're mistaken. If we're talking incentives, *nothing* matches demonstrating impact! Will blog on this soon.
@prajdabre1
You try hard…
CMU-Qatar have 1.5 teaching track faculty that does NLP and barely funding for research
So I reached out to people on other ppl on social media- learning by doing
It just that you need to get used to rejections ALL THE TIME
@anpaure
@felpix_
How do you evaluate?
Do you do like a research hackathon and mark how many ARR submissions these high school kids can make within a certain period of time?
Any interesting NLP work in digital humanities?
I dunno- I have been recently interested in taking humanities/social science students jobs
Hahahahahahah
I am thinking about CMU-Portugal…
But again, I don’t want to be ended up in an AI desert like Qatar…
And again, how am I gonna get any PhD position anyway…
I just received the EMNLP reviews, and the quality exceeded my expectations. Thank you to all the area chairs and reviewers for their excellent work and service.🤗
WAIT, it's not over; Meta just dropped the LLM Compiler! 🧑💻
> Beats GPT-4 on code size improvement and disassembly
> Achieves 77% of the optimising potential of an autotuning search and 45% disassembly round trip
> Built on top of CodeLLaMa with improved code optimisation and
This mirrors my experience. "Analysis of research articles and patent applications shows that members of teams that collaborate remotely are less likely to make breakthrough discoveries than members of on-site teams."