Yan Xu

Tencent; PhD@HKUST CAiRE; Previously interned in Amazon Alexa AI

[Yan Xu @Tea_XuYan]

My Ph.D. supervisor Prof. Pascale Fung @pascalefung is hiring Ph.D. students for fall 2024. Please feel free to send her emails ([email protected]) if you’re interested!😊

[Yan Xu @Tea_XuYan]

@JasonForJoy Congrats!!!

[Mahdi Namazifar @Namazifar]

Our KILM paper was accepted at ACL 2023! In this paper with @Tea_XuYan, @hdevamanyu, Di Jin, @AishwaryaPadma4, Yang Liu, and @dilekhakkanitur we show how atomic pieces of knowledge could be injected into a pre-trained language model. https://t.co/PBzz8v33dc @AmazonScience

[Samuel Cahyawijaya @SCahyawijaya]

I'm very happy to announce that NusaCrowd, a crowdsourcing collaboration for centralizing Indonesian corpora, is accepted in #ACL2023 Findings: https://t.co/Y8ppKcQLpc

It is a BIG momentum for IndoNLP to push datasets to be open & publicly accessible 🇮🇩🇮🇩🇮🇩

#IndoNLP #NLProc

[Genta Winata @gentaiscool]

🚨 We are excited to have our NusaCrowd paper accepted in #acl2023 Findings. It is the first collaborative initiative to collect Indonesian corpus 🇮🇩

It is a BIG momentum for IndoNLP to push datasets to be open & publicly accessible.
https://t.co/en9E0C2Hye #NLProc @aclmeeting

[Yan Xu @Tea_XuYan]

@Vfrz525_ What? even MSR"A"? mama mia

[Yan Xu @Tea_XuYan]

It is so funny to see how similar names are iterated in different papers.🤡

[Raj Dabre @prajdabre]

https://t.co/nuzWZIkRlr
FFS what is LLaMA-adapter? Just looks like prefix tuning with a learnable weight for the prefix part of self-attention. I wish people would stop pretending like they invented new things.

[Yan Xu @Tea_XuYan]

@WoutervD Meow?

[Samuel Cahyawijaya @SCahyawijaya]

🚨 Exciting news! We are delighted to announce NusaCrowd, a new open-source initiative to collect and unite Indonesian NLP resources! 🇮🇩🇮🇩🇮🇩

Through NusaCrowd, we have gathered 137 datasets and 117 standardized data loaders covering text, audio, and image modalities💪🏾✨💕🌍

[Yan Xu @Tea_XuYan]

@Namazifar Congratulations🌟

[Chelsea Finn @chelseabfinn]

Large language models (LLMs) often make mistakes that are difficult to correct.

We study the problem of quickly editing these models:
Paper: https://t.co/iJCrvbcga3
Code: https://t.co/8zMmIl9WdI

w/ @_eric_mitchell_, C. Lin, @ABosselut, @chrmanning

thread 🧵👇

[Yan Xu @Tea_XuYan]

@KCrosner Congrats!

[Genta Winata @gentaiscool]

We just released the IndoNLU benchmark Github repository at https://t.co/Hzac4Gf04q ⭐️✨The largest benchmark for Indonesian NLP so far. You can find our open-source datasets, pre-trained models, and the starter code! #nlproc #aacl #acl #nlp #indonlp #indonlu #indobenchmark (1/n)

[Yan Xu @Tea_XuYan]

A nice work from CAiRE lab~ The code has been released https://t.co/dT2ea5tEbz

[Genta Winata @gentaiscool]

After a day waiting... happy to announce that our meta-learning ASR paper "Learning Fast Adaptation on Cross-Accented Speech Recognition" is accepted by Interspeech 2020. We propose a benchmark for zero-shot & few-shot settings #interspeech
Preprint https://t.co/tr6yQkcPzy

[Yan Xu @Tea_XuYan]

A joke i got these days🤭

[clara T @ramencult]

All of this is his fault

[William Wang @WilliamWangNLP]

Attending your first academic conference...

[Yan Xu @Tea_XuYan]

Winter is coming👏🏻👏🏻👏🏻