Kyunghyun Cho @kchonyc Twitter profile

Last Seen Profiles

@Dustinx_Bs12

@joel11029338

@R0b3r70V

@basticarolino

@sa288bri

@CarterJame89017

@JakobTarp127989

@mmers

@croatiankim

@SeanBormanNFL

@TheWynyardFc

@ReemNou76047840

@BambiPichl72356

@FecafootOfficie

@bigolmtwndew

@tatti11131

@ANNVYSHINSKY

@usRose410964

@AhmedAlawadhii

@NewhartGra62492

@GulamAliKhatana

@Lyzas4

@yessicaddict_

@yokizle

@MindiA94029

@andrewko1214

@KiraTaylor15

@MakeevaVar10763

@YahayaJoelMusa2

@Deegoddess888

@TLH_Football

@IbcSulaiman

@RealmSpaceGame

@shrutipandalai

@BrunsonMol48435

@PranibN43675

Kyunghyun Cho

@kchonyc

3 years

i was honored to receive the inaugural samsung AI researcher award. i’ve donated prize money to @Mila_Quebec to support newly arriving female students from latin america, africa, south asia, south east asia and korea. easiest decision ever: read more at

MilaQuebec

@Mila_Quebec

3 years

Mila alumnus Kyunghyun Cho @kchonyc makes a financial contribution to support female PhD and postdoctoral fellows in order to promote equity and diversity at Mila and within the AI community.

1

11

223

36

83

1K

Kyunghyun Cho

@kchonyc

3 years

i've received the Ho-Am Prize (Engineering) which comes with a pretty substantial cash prize. i plan to spend it for a few causes close to my heart in the next few weeks. here goes the first one:

24

41

669

Kyunghyun Cho

@kchonyc

6 years

“We’re machines,” says Hinton. “We’re just produced biologically. Most people doing AI don’t have doubt that...

8

253

623

Kyunghyun Cho

@kchonyc

6 months

ok here you go. my prediction: 1. ilya sutskever becomes CEO. 2. geoff hinton joins the OpenAI board.

32

24

613

Kyunghyun Cho

@kchonyc

26 days

once @ylecun told me (heavily paraphrased), it's not F=ma but \min (F-ma)^2. i didn't realize its importance, but it is perhaps the most enlightning perspective i've ever heard.

44

42

604

Kyunghyun Cho

@kchonyc

1 year

so.. i guess they haven’t heard the news yet… should i break it to them?

13

10

579

Kyunghyun Cho

@kchonyc

2 years

some mathematicians will shortly write papers explaining her behaviour in a principled and rigorous way.

Francesco Orabona

@bremen79

2 years

When you debug a machine learning model

35

207

1K

16

45

541

Kyunghyun Cho

@kchonyc

3 years

"a scientist who is applying machine learning techniques to a domain has a responsibility to take that domain somewhat seriously."

A Flawed Dataset for Symbolic Equation Verification

Arabshahi, Singh, and Anandkumar (2018) propose a method for creating a dataset of symbolic mathematical equations for the tasks of symbolic equation verification and equation completion....

arxiv.org

7

86

541

Kyunghyun Cho

@kchonyc

3 years

students are curious, and their questions are great: a few select questions from this semester, and my (incomplete) answers at

11

107

526

Kyunghyun Cho

@kchonyc

5 years

re "Why not consider other models? such as XLNet": I agree with the reviewer on the importance of time travel research, but it's slightly out of the scope of this paper.

10

69

522

Kyunghyun Cho

@kchonyc

5 years

ahahahahahahahahahaha

8

84

496

Kyunghyun Cho

@kchonyc

3 years

OMG! my alma mater chose me as the Alumnus of the Year! Kiitos paljon!

Computer Science

@CSAalto

3 years

Aalto School of Science has just selected our alumnus Kyunghyun Cho as the Alumnus of the Year! 🥳He defended his doctoral thesis at Aalto in 2014 and is now associate professor of computer science and data science at New York University. Big congratulations Kuynghyun Cho!

1

7

101

25

14

471

Kyunghyun Cho

@kchonyc

6 months

if you trust @GoogleDeepMind Gemini about itself, it has 1.56 trillion parameters and cost Google $1-2billion (as opposed to GPT-4 which cost OpenAI $500M.) there were more than 100 engineers in the team who worked on Gemini. jailbreak by 한국어 🤣🤣🤣

21

71

465

Kyunghyun Cho

@kchonyc

2 years

i don’t know why anyone, including myself; spends any time working on ML when everything was invented early 90s.

Jürgen Schmidhuber

@SchmidhuberAI

2 years

30 years ago: Transformers with linearized self-attention in NECO 1992, equivalent to fast weight programmers (apart from normalization), separating storage and control. Key/value was called FROM/TO. The attention terminology was introduced at ICANN 1993

26

140

1K

21

28

438

Kyunghyun Cho

@kchonyc

4 years

We must now realize the promise of AI by trusting Turing, unifying our framework and building our algorithm. I am running for president of the United States!

9

16

441

Kyunghyun Cho

@kchonyc

4 years

Do you and your org have ML/NLP/DS questions but not have anyone to talk with about them? I’d like to listen to your problems, talk about them and brainstorm ways forward with you. See

17

80

439

Kyunghyun Cho

@kchonyc

2 months

machine learning without model selection is biology without evolution. any claim of state of the art is vacuous without model selection, and indeed some were in continual learning.

Sungmin Cha

@_sungmin_cha

2 months

Exciting news! Our recent research paper, "Hyperparameters in Continual Learning: a Reality Check," is now available on arXiv! Check it out at .

1

6

54

3

11

88

Kyunghyun Cho

@kchonyc

2 years

let me help them out: “:q”

8

18

436

Kyunghyun Cho

@kchonyc

5 years

ICML 2021 in SEOUL, KOREA!

9

52

390

Kyunghyun Cho

@kchonyc

4 years

even more counterintuitive is that we are still using "inches"

Fermat's Library

@fermatslibrary

5 years

Here's a useful counterintuitive fact: one 18 inch pizza has more 'pizza' than two 12 inch pizzas

1K

27K

65K

4

27

386

Kyunghyun Cho

@kchonyc

5 years

77

15

378

Kyunghyun Cho

@kchonyc

4 years

doesn't everyone check out my homepage regularly? 🤪 apparently not 😅 to save some people's time (and my time), i've quit FAIR a couple of months ago: i.e. sorry, i can't take you in as an intern at FAIR. it's me, not you.

10

7

366

Kyunghyun Cho

@kchonyc

1 year

so, elon thinks he can catch up with OpenAI in 6 months.

20

11

360

Kyunghyun Cho

@kchonyc

4 years

NYC cheering was faster than any mobile notification!

4

9

361

Kyunghyun Cho

@kchonyc

8 months

so, how many of your papers are about to become irrelevant?

16

29

348

Kyunghyun Cho

@kchonyc

5 years

thinking about spending 1/2 lecture next spring for ug intro to ml on kalman filter by teaching it as an extension of PCA and showing them how to estimate posterior and/or parameters by backprop (e.g., ) any thoughts?

7

61

349

Kyunghyun Cho

@kchonyc

4 years

i’ve experienced how elections happen in a few countries, _but_ when it comes to the complexity and ridiculousness of the rules and system, US beats the hell out of all the others.

6

8

347

Kyunghyun Cho

@kchonyc

4 years

i'm quite embarrassed and wanted to sweep it under a rug, but let me share what happened behind this, largely for my own record/reminder and for a small hope this might raise awareness.

Vector Institute

@VectorInst

4 years

@tarfandy @KKofahi @kchonyc @SPOClab We humbly accept your comment. In this case our marketing and keynote lineup did not reflect the diversity of the full program and we thank @kchonyc and @hhexiy for graciously stepping up to do the right thing. Our new, full lineup can be found here:

0

19

14

16

352

Kyunghyun Cho

@kchonyc

3 years

about 90% of what i often teach in <Intro to ML> is in this paper from 1962:

4

43

349

Kyunghyun Cho

@kchonyc

5 years

slides from my keynote talk at #emnlp2019

EMNLP Keynote.pptx

drive.google.com

4

83

338

Kyunghyun Cho

@kchonyc

6 years

thanks, @NvidiaAI , for the shiny new Titan V!

11

26

340

Kyunghyun Cho

@kchonyc

6 years

OMG *geoff hinton* nominated me for this

CIFAR

@CIFAR_News

6 years

CIFAR Azrieli Global Scholar @kchonyc @NYUDataScience nominated by Geoffrey Hinton as one of @Bloomberg 's people to watch in 2018:

0

10

50

17

23

336

Kyunghyun Cho

@kchonyc

2 years

until @gmail figures out how to block SEO spam mails that all look the same, i will completely ignore every single paper from @GoogleAI on few-shot learning for NLP.

10

21

327

Kyunghyun Cho

@kchonyc

1 year

best neurips ever

11

10

318

Kyunghyun Cho

@kchonyc

5 years

"Due to our concerns about malicious applications of [Our model ... trained simply to predict the next word], we are not releasing the trained model" for the humanity, i feel now obliged to remove all the pretrained model weights i've made public so far. 😅

OpenAI

@OpenAI

5 years

We've trained an unsupervised language model that can generate coherent paragraphs and perform rudimentary reading comprehension, machine translation, question answering, and summarization — all without task-specific training:

172

3K

6K

9

63

308

Kyunghyun Cho

@kchonyc

1 year

the highlight of #iclr2023

11

1

304

Kyunghyun Cho

@kchonyc

2 years

earlier we open-sourced the code and also trained models for breast cancer screening from (led by @NanWu__ , @kjgeras et al.) based on our own data () at .

GitHub - nyukat/breast_cancer_classifier: Deep Neural Networks Improve Radiologists' Performance in...

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening - nyukat/breast_cancer_classifier

github.com

1

56

287

Kyunghyun Cho

@kchonyc

1 year

i just can't watch _that_ senate hearing beyond some select excerpts. i can't believe the discourse on AI is about "oh AI may kill all of us unless i get to dictate wtf should be done" by a few clueless dudes, without any discussion on some immediate benefits & harms. (1/2)

11

40

285

Kyunghyun Cho

@kchonyc

5 years

super nervous

emnlp2020

@emnlp2020

5 years

We'd like to announce the keynote speakers for EMNLP-IJCNLP 2019: Meeyoung Cha (KAIST), Kyunghyun Cho @kchonyc (NYU & FAIR), and Noam Slonim @noamslonim (IBM).

0

15

103

10

6

280

Kyunghyun Cho

@kchonyc

4 years

since everyone loves/hates ranking authors based on their submissions/acceptances to #ICLR2020 , here's another rank i just created based on the # of letters in their names. @svlevine does not show up in top-50 (one with all names, and the other with the first name segments only)

5

14

275

Kyunghyun Cho

@kchonyc

10 months

if i ever leave @nyuniversity , you know which university i will be at

5

0

262

Kyunghyun Cho

@kchonyc

6 years

aftr numerous rejections and improvrments, the paper's finally accepted and published officially. great work by Zhengping Che, Sanjay Purushotham, @david_sontag and @yanliu_usc

13

52

261

Kyunghyun Cho

@kchonyc

5 months

btw, it took 12 years, but i did end up having a dinner with CL last year

Kyunghyun Cho

@kchonyc

5 months

some absolutely not-plagiarised text snippets in my dissertations: * "it would not have been possible for me to survive long, freezing, snowy winter of Finland without songs from four girls of 2NE1 (especially, the leader CL)."

1

59

9

7

257

Kyunghyun Cho

@kchonyc

3 years

"... NL[P] ... scientists themselves completely forget what natural language is like." - Ernest Davis (2021) it's only April, and we've got the best quote of 2021 candidate.

4

29

254

Kyunghyun Cho

@kchonyc

1 year

before and after #iclr2023

7

2

255

Kyunghyun Cho

@kchonyc

2 years

enjoying this awesome tutorial on conformal prediction by @ml_angelopoulos & @stats_stephen : . what a nice, straightforward framework to think of UQ in practical terms. there’s an associated tutorial paper as well: .

A Gentle Introduction to Conformal Prediction and...

Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty quantification to avoid consequential model failures. Conformal...

arxiv.org

9

43

249

Kyunghyun Cho

@kchonyc

3 years

David Blei has an interesting signature

3

8

249

Kyunghyun Cho

@kchonyc

2 years

another motivational AI tweet drop 💣 prompt engineering is a symptom not a cure and must be treated not encouraged.

14

23

243

Kyunghyun Cho

@kchonyc

5 years

congratulations to @ylecun for the turing award. we, CILVRies, couldn't resist but present him with a physical obligatory Le Cake. (photo credit Y-Lan Boureau)

7

21

242

Kyunghyun Cho

@kchonyc

3 years

which graduate program would admit me? no UG research experience+very low GPA+no GRE ever+expired but reasonable toefl hmm..

Delip Rao e/σ

@deliprao

3 years

Every few years, I feel like I need re-education. What graduate program you would go to today if you were math/quantitatively inclined?

29

5

106

11

5

242

Kyunghyun Cho

@kchonyc

4 months

not a single commercial LLM can sort the list of ~100 references according to the last name of the first author. so disappointing.

34

10

238

Kyunghyun Cho

@kchonyc

3 years

what a simple yet effective idea! :) looking at it from the architectural depth perspective ( by zheng et al.,) the depth (# of layers between a particular input at time t' and output at time t) is now (t-t') x L rather than (t-t') + L.

Sainbayar Sukhbaatar

@tesatory

3 years

We updated our Feedback Transformer paper with new experiments. Transformers fail on very simple algorithmic tasks as it is a feedforward model. A simple fix is to attend to higher-level representations (it's like remembering our past thoughts)

11

89

545

1

48

241

Kyunghyun Cho

@kchonyc

7 months

very much enjoyed this paper (), but reading the paper makes this field look more psychology than machine learning; not sure if i'll enjoy the field as much as i did this paper when this trend goes further.

Reasoning or Reciting? Exploring the Capabilities and Limitations...

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or...

arxiv.org

8

33

241

Kyunghyun Cho

@kchonyc

5 years

NYC the city of machine translation

5

15

233

Kyunghyun Cho

@kchonyc

1 month

a nice study by Merrill, Petty & Sabharwal. it looks like i won't have to wait too much longer for the reinvention of LSTM/GRU by LLM bros.

The Illusion of State in State-Space Models

State-space models (SSMs) have emerged as a potential alternative architecture for building large language models (LLMs) compared to the previously ubiquitous transformer architecture. One...

arxiv.org

8

28

229

Kyunghyun Cho

@kchonyc

4 years

ahahahaha @geoffreyhinton hasn’t managed to “publish” the idea in his talk from 1973 yet but plans to do so “soon”

13

12

226

Kyunghyun Cho

@kchonyc

2 years

now @YejinChoinka can't deny she's a genius

MacArthur Foundation

@macfound

2 years

Computer Scientist @YejinChoinka uses natural language processing to develop AI systems that can understand language and make inferences about the world. Learn more about the 2022 MacArthur Fellow #MacFellow

17

81

579

5

18

220

Kyunghyun Cho

@kchonyc

8 months

prediction: @OpenAI will announce within six months that they are from there on exclusively using sourced (and often paid for) data and stop using freely crawled data for their language models.

28

12

223

Kyunghyun Cho

@kchonyc

3 years

i endorse Fig. 1

Jason Weston

@jaseweston

3 years

(1/2) 🚨 Our new work! 🚨 "Retrieval Augmentation Reduces Hallucination in Conversation" @shtruk @spencerpoff @moyapchen @douwekiela @jaseweston We infuse dialogue models with knowledge, significantly reducing hallucinated facts during conversation.

3

50

269

3

14

223

Kyunghyun Cho

@kchonyc

2 years

here's the recordings of the lectures from this Fall on deep learning for natural language processing:

DS-GA 1011 (Fall 2021) Deep Learning for Natural Language Processing

the slides (not polished and mostly for my own references): https://drive.google.com/drive/folders/1ykXBtophaY_65VHK_8yDzZQJwfJDD5Ve?usp=sharing the handwrit...

www.youtube.com

Kyunghyun Cho

@kchonyc

2 years

0

19

87

6

42

218

Kyunghyun Cho

@kchonyc

3 years

... paid for by Microsoft:

Microsoft invests in and partners with OpenAI to support us building beneficial AGI

Microsoft is investing $1 billion in OpenAI to support us building artificial general intelligence (AGI) with widely distributed economic benefits. We’re partnering to develop a hardware and software...

openai.com

Ilya Sutskever

@ilyasut

3 years

Deep learning is a free lunch

74

99

1K

7

21

219

Kyunghyun Cho

@kchonyc

2 years

well :) 5 years too late but still happy to receive the best research paper award cc ⁦ @orf_bnw ⁩ ⁦ @caglarml ⁩ ⁦ @imkelvinxu ⁩

18

5

219

Kyunghyun Cho

@kchonyc

1 year

not everything we learn needs to be for the next paper 😩

5

7

220

Kyunghyun Cho

@kchonyc

4 years

it has arrived! @jacobeisenstein

5

17

217

Kyunghyun Cho

@kchonyc

3 years

it's a bit embarrassing, but we've come to learn the RTRL-based online hparam opt in our was proposed earlier by Luca Franceschi et al. (S3.2 in ).

5

8

218

Kyunghyun Cho

@kchonyc

1 year

Bing suspended itself from using the Bing Image Creator while trying to help me out ... i'm sorry

8

25

214

Kyunghyun Cho

@kchonyc

2 years

wait... hold on... this is the panel i signed up for...? why are my hands and eyes shaking?

Rishabh Agarwal

@agarwl_

2 years

Acknowledging that there is no consensus on best evaluation practices for ML, the workshop would also have 3 panel discussions. The 1st panel discussion would be about "Incentives for Better Evaluation", featuring researchers who have seen the field of ML explode. [3/N]

2

4

26

4

7

216

Kyunghyun Cho

@kchonyc

6 years

the paper behind BERT is now online: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

BERT: Pre-training of Deep Bidirectional Transformers for Language...

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is...

arxiv.org

0

67

213

Kyunghyun Cho

@kchonyc

3 years

all, may i suggest we stop blindly averaging scores from different tasks? if i average the (normalized) scores from a game of baseball, a game of soccer and a game of basketball played by each city, rank the cities and claim one city is better than others, what would you call me?

20

9

213

Kyunghyun Cho

@kchonyc

5 years

"The traditional declarative programming model of building a graph and executing it via a tf.Session is discouraged" the end of an era

Release TensorFlow 2.0.0 · tensorflow/tensorflow

Release 2.0.0 Major Features and Improvements TensorFlow 2.0 focuses on simplicity and ease of use, featuring updates like: Easy model building with Keras and eager execution. Robust model deploym...

github.com

3

42

208

Kyunghyun Cho

@kchonyc

7 years

DeepMind aims at solving AGI, but AV doesn't work.. :(

14

33

207

Kyunghyun Cho

@kchonyc

4 years

I got my degrees from the top university in the world (sorted alphabetically)

Julian Togelius

@togelius

4 years

This is a good post. It's true that top universities get an avalanche of applications from people wanting to do AI/ML PhDs. And published research is a very good indicator of research potential. But there are other universities than the top ones and other conferences than NeurIPS

6

51

257

5

204

Kyunghyun Cho

@kchonyc

2 years

one of them leads 25M followers and the other has 30k followers on twitter

8

0

203

Kyunghyun Cho

@kchonyc

23 days

a new blog post, because it is Saturday. <Fixing DPO but I have a dinner reservation …>

5

32

204

Kyunghyun Cho

@kchonyc

7 months

a number of weird definitions and weirdly specific points, but overall, worth reading it to see which areas are considered as priorities by WH. in this 🧵, let me copy-paste those few weird/interesting/specific points i found reading it.

Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence...

By the authority vested in me as President by the Constitution and the laws of the United States of America, it is hereby ordered as follows: Section 1. Purpose. Artificial intelligence...

www.whitehouse.gov

5

43

199

Kyunghyun Cho

@kchonyc

4 years

I WON. I WON THE ELECTION.

13

4

200

Kyunghyun Cho

@kchonyc

1 year

. @MinaLee__ starts her talk at @nyuniversity an hour after GPT-4 was released. both exciting and nervous 😂😂😂

2

7

198

Kyunghyun Cho

@kchonyc

4 years

#acl2020nlp bonnie webber walked up to me and told me after one of my talks quietly* "i don't think you have any idea what discourse is" which i could only nod in agreement. congratulations! (*) probably to save me from embarrassment

2

8

195

Kyunghyun Cho

@kchonyc

1 year

i may be as well

17

6

194

Kyunghyun Cho

@kchonyc

3 years

A Lecture on NLP from Big Ideas in Artificial Intelligence (): This is the NLP section of the course organized by NYU in Spring 2021. These are preliminary recordings which were edited and polished for the final versions.

Lecture on NLP in Big Ideas in AI: Teaser

null

www.youtube.com

3

34

192

Kyunghyun Cho

@kchonyc

3 years

🤯 from the NeurIPS tutorial by @ChengSoonOng and @mpd37

9

14

189

Kyunghyun Cho

@kchonyc

2 years

ICML 2023 will happen in Hawaii not in Seoul. yes, i understand your frustration (think of my own frustration as well ...) i've seen how this decision was made and can tell you it wasn't a light decision. thanks for your understanding! see for more info.

4

27

191

Kyunghyun Cho

@kchonyc

3 years

""" Notable individual investors in the round include ... NBA star Kevin Durant ... """ !?

VentureBeat

@VentureBeat

3 years

Hugging Face triples investment in open source machine learning models by @kharijohnson

1

28

83

9

11

187

Kyunghyun Cho

@kchonyc

7 years

My lecture note for the undergrad course <Intro to Machine Learning> from this Spring (2017) is available online...

0

50

186

Kyunghyun Cho

@kchonyc

10 months

#ICML2023 begins!

4

1

185

Kyunghyun Cho

@kchonyc

3 years

the breiman lecture on causal learning by Marloes Maathuis is clear and well-delivered to the degree that i am having a false sense that i actually understand causal inference.

5

14

183

Kyunghyun Cho

@kchonyc

3 years

is it because it’s easier developing an AI driver than an AI car?

Engadget

@engadget

3 years

Tesla is working on an AI-powered humanoid robot

61

150

820

7

17

179

Kyunghyun Cho

@kchonyc

3 years

my friends, how do you feel to have become meta employees? ;)

10

3

180

Kyunghyun Cho

@kchonyc

1 year

disappointed we plan to release reviews hopefully tomorrow but hey what can we do at this rate? #ICML2023 ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░ 92.41%

26

7

183

Kyunghyun Cho

@kchonyc

2 years

quite a few people told me earlier LM & MT were just applications and they wanted to do "core" ML research. i wonder what they are thinking and doing now 🤣 are you all scaling up?

9

11

180

Kyunghyun Cho

@kchonyc

6 months

the only concrete take-away i got over the past few days is that i can't rely on a single service provider of LM to build any LM-powered applications. too fragile and too risky.

11

25

178

Kyunghyun Cho

@kchonyc

5 months

i mean it isn’t that surprising, is it? here’s a prescient whatsapp convo from 2021.

Chomba Bupe

@ChombaBupe

5 months

An explanation for why GPT-4 is degrading: "... we find that on datasets released before the LLM training data creation date, LLMs perform surprisingly better than on datasets released after" New tasks are difting away from what GPT-4 was trained on.

49

422

2K

6

13

175

Kyunghyun Cho

@kchonyc

4 years

before too late, let me thank the volunteers without whom we couldn't have run ICLR'20 virtually: #ICLR2020 @iclr_conf

3

14

171

Kyunghyun Cho

@kchonyc

3 years

it's a double-embarrassment day. NaturalProof in , which i loved working on, turned out also to be a repetition of the work by Deborah Ferreira .

6

10

173

Kyunghyun Cho

@kchonyc

5 years

HYPE: a @PyTorch based library for embedding a graph in a hyperbolic space @mnick

3

37

167

Kyunghyun Cho

@kchonyc

5 years

my strategy is to wait for Sam to share some of those on our group slack

6

5

169

Kyunghyun Cho

@kchonyc

4 months

i wrote this proposal back in 2017. NSF rejected it & the panel found it "Low Competitive". grant rejection is an everyday affair, but i felt particularly bitter about this one. its title was <End-to-End Search Engine-Guided Query-Driven Summarization>.

7

12

165

Kyunghyun Cho

@kchonyc

4 years

i wanted to briefly share why i joined @NYUDataScience 5yrs ago and how i've liked it so far:

2

22

166

Kyunghyun Cho

@kchonyc

3 years

do you want a language understanding evaluation suite for a new language, but you don’t know where to start? we didn’t either. check out KLUE:

KLUE: Korean Language Understanding Evaluation

We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual...

arxiv.org

5

27

165

Kyunghyun Cho

@kchonyc

3 years

Bong Joon-Ho (yes, that Bong Joon-Ho) is the recipient in the area of art. i haven't complained much about the on-going pandemic myself, but man.. i can't believe i'm missing this 1-in-a-lifetime oppt to meet Bong Joon-Ho because of the pandemic. i'm so furious at covid-19.

NYU Data Science

@NYUDataScience

3 years

Let's all give a HUGE congrats to CDS faculty @kchonyc for being awarded a 2021 Samsung Ho-Am Prize in the field of Engineering! His award recognizes his work in developing a neural machine translation algorithm that can provide high-quality translations.

6

14

200

8

1

166