Yiran "Lawrence" Luo

I study languages and related stuffs. PhD guy at @SCAI_ASU.

[Cogint ASU @CogintASU]

Congrats to Cogint-ASU (https://t.co/RFcI5LLHfE) members for papers accepted to #ACL2022. Welcome to stop by for a presentation or poster session. Looking forward to your attendance!
@Swarooprm7 @nrj_varshney @trgokhale @Ju55Pratyay @manluo12 @Mihir3009 @FPSLuozi @cbaral (1/14)

[/MachineLearning @slashML]

A Few Helpful PyTorch Tips (Examples Included) https://t.co/9MKf4ChXnM

[Yiran "Lawrence" Luo @FPSLuozi]

好！很有精神！（指老莱

[Linus Tech Tips @LinusTech]

25000 Volts hurt - @ElectroBOOMGuy

[Yiran "Lawrence" Luo @FPSLuozi]

哈↑哈↑哈↑哈↑哈↑

[Delton Ding @DeltonDing]

完蛋了。我偶然看到某个 YouTube 频道，看了整整一天。我现在满脑子都是 Hyper meaning high, Hypo meaning low.

[Yiran "Lawrence" Luo @FPSLuozi]

@PhillyD Not the only one to see this encoding error. No worry. Take your time (:

[Yiran "Lawrence" Luo @FPSLuozi]

@ElectroBOOMGuy @pewdiepie Kinda reminds me of this

[Yiran "Lawrence" Luo @FPSLuozi]

@ElectroBOOMGuy @YouTube Wow that's a milestone! Congrats!

[Mehdi Sadaghdar @ElectroBOOMGuy]

Hey, is there an award for #1 MOST SUBSCRIBED IRANIAN YOUTUBER?!
Well I'm also Canadian, but I won't win in that category...
Also YouTube is blocked in Iran so a lot of talents don't get to show, which is unfair!
BUT HAY I'M #1 ANYWAY... at least for now... @YouTube

[Stanford NLP Group @stanfordnlp]

Our new-ish, neural, pure Python stanfordnlp package provides grammatical analyses of sentences in over 50 human languages! https://t.co/p6MhHyHLC2 Version 0.2.0 brought sensibly small model sizes and an improved lemmatizer. Try it out: pip install stanfordnlp

[Yiran "Lawrence" Luo @FPSLuozi]

Check it out! I donated to 'Help KyoAni Heal' - https://t.co/PFzVU03BoL via @gofundme

[Quoc Le @quocleix]

Nice blog post titled "The Quiet Semi-Supervised Revolution" by Vincent Vanhoucke. It discusses two related works by the Google Brain team: Unsupervised Data Augmentation and MixMatch.

https://t.co/7nEFUgX8a1

[PyTorch @PyTorch]

A walkthrough of the PyTorch Internals by core developer @ezyang .
It's a great resource if you want to contribute to PyTorch.
https://t.co/enpD4TKjeS

[Yiran "Lawrence" Luo @FPSLuozi]

Paper Dissected: "Attention is All You Need" Explained https://t.co/7x8aX5sQIx

[(((ل()(ل() 'yoav))))👾 @yoavgo]

I expected the Transformer-based BERT models to be bad on syntax-sensitive dependencies, compared to LSTM-based models.

So I run a few experiments. I was mistaken, they actually perform *very well*.

More details in this tech report: https://t.co/6hV9YoOvN8

[Yiran "Lawrence" Luo @FPSLuozi]

An Overview of Multi-Task Learning for Deep Neural Networks https://t.co/oEzg956Rvk

[Yiran "Lawrence" Luo @FPSLuozi]

@ywwuyi 总之先染白毛

[Yiran "Lawrence" Luo @FPSLuozi]

Random Initialization For Neural Networks : A Thing Of The Past by @aditya69398232 https://t.co/1BsUbjghP7

[L. Dietz @[email protected] @[email protected] @lauradietz99]

Text books are great, but for the latest research you have to read research papers. Be aware that conclusions are based only on one person's view and may never make it into a text book. Reading a research paper requires a critical dialogue. Here is how: https://t.co/GEIXjROTSI

[Yiran "Lawrence" Luo @FPSLuozi]

Aa a buckeye, respects https://t.co/pHml0pKAyp

[Michigan Athletics 〽️ @UMichAthletics]

Stay safe, Buckeyes.