Xinyu Yuan @XinyuYuan402 Twitter profile

Last Seen Profiles

@ldkong1205

@pcgroveacademy

@DeutscheBank

@Karina_SexGirl

@namachan10777

@bokeplokalmalam

@SEN_815

@cokeainechick

@IsiahWhitlockJr

@Maximow21987525

@sugatasaek82821

@mountainbunny1

@istrismart1

@remuslupnx

@1fortyproject

@xochilily

@joaomarinhosp

@Holdangeldragon

@Ryoo18R

@ibrahim_____74

@WhatActHapp

@aelmamenter

@OTBCRyan

@Saudi_S511

@samvcxz

@kuroyasume12984

@Benpablo98

@mrsbeasleycpa

@eito12

@JesseWittenrich

@initokyolagi

@CuttleB0ne

@Bendor82

@BergoHijab

@esmio0524

@EIPFun

Xinyu Yuan

@XinyuYuan402

1 year

Excited to announce our ICML2023 Oral paper, ProtST! It's a general framework that enhances protein sequence pre-training and understanding with biomedical texts. Discover more:

GitHub - DeepGraphLearning/ProtST: [ICML-23 ORAL] ProtST: Multi-Modality Learning of Protein...

[ICML-23 ORAL] ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts - DeepGraphLearning/ProtST

github.com

7

9

59

Xinyu Yuan

@XinyuYuan402

11 months

Never thought I myself would run into any plagiarism-related issue in such way … (our A*Net paper is plagiarized by an ICLR submission) @iclr_conf we all authors call for some serious actions on this matter. Some LINES should NOT be crossed.

Zhaocheng Zhu

@zhu_zhaocheng

11 months

Really shocked today... My paper A*Net has been on arXiv for more than a year, and it was plagiarized in an ICLR submission. There is no reference to A*Net and more than half of the methodology is identical to my paper. @iclr_conf any solution? up: my A*Net. down: plagiarism.

23

70

646

1

4

54

Xinyu Yuan

@XinyuYuan402

1 year

Our foundation model for knowledge graphs (KGs)!✨ It tackles a interesting and important problem that different KGs have different vocabulary of relations and entities, thus cannot be modeled by a shared network in the first glance. Unifying models for KGs now is possible!

Michael Galkin

@michael_galkin

1 year

🎉New paper alert! It’s time to announce ULTRA - a pre-trained foundation model for knowledge graph reasoning that works on _any_ graph and outperforms supervised SOTA models on 50+ graphs. Arxiv: Code: 🧵1/n

4

69

292

1

4

41

Xinyu Yuan

@XinyuYuan402

1 year

Just created a repo "awesome-single-cell-foundation" for paper collection of single cell foundation models. ➡️

GitHub - KatarinaYuan/awesome-single-cell-foundation: Paper collection for single cell foundation...

Paper collection for single cell foundation models - KatarinaYuan/awesome-single-cell-foundation

github.com

1

28

Xinyu Yuan

@XinyuYuan402

9 months

See our ULTRA at #ICLR2024 !! 🎉🎉🎉

Michael Galkin

@michael_galkin

9 months

ULTRA got accepted to #ICLR2024 - see you in Vienna :) More importantly though, my dear co-author @XinyuYuan402 just collected her first 🏆 Grand Slam 🏆 of ML conferences (ICML -> NeurIPS -> ICLR in one cycle)! 🎉

3

8

76

1

25

Xinyu Yuan

@XinyuYuan402

1 year

I will be at #ICML2023 from 23rd to 30th 😃 I will have an oral presentation for our ProtST project with @MinghaoXu_Alan and present a poster at KLR workshop () for A*Net, a joint work with @zhu_zhaocheng . Would love to chat about LLM and AI4Science!!

Knowledge and Logical Reasoning in the Era of Data-driven Learning

Workshop at ICML 2023

klr-icml2023.github.io

Minghao Xu

@MinghaoXu_Alan

1 year

Will be at @icmlconf next week and have an oral presentation of our ProtST project along with @XinyuYuan402 . Happy to chat about protein design, AI4Science, multimodal LLM and meet old/new friends! ProtST paper: ProtST code:

0

19

0

5

20

Xinyu Yuan

@XinyuYuan402

1 year

📢 Great job! Our awesome collaborator @santiagomiret just penned an insightful blog about our ICML spotlight work ProtST. Dive in to see how a user can simply input the description of a protein to retrieve the corresponding proteins

1

4

17

Xinyu Yuan

@XinyuYuan402

1 year

Super super nice, supportive, knowledgeable and aspiring supervisor and collaborator when I had an internship at @IntelAI . ⭐️ apply it now and then get to learn all those valuable qualities from him!!!

Michael Galkin

@michael_galkin

1 year

Our graph team at @IntelAI is looking for an intern to work on foundation models for Graph ML including (but not limited to) KG reasoning and scalable GNNs. Fully remote is ok, starting date: the sooner the better 😉 Application portal: DMs are open

6

40

200

0

12

Xinyu Yuan

@XinyuYuan402

1 year

Quote and quote from my awesome collaborators!

Michael Galkin

@michael_galkin

1 year

Our A*Net will be at NeurIPS'23 (as well as another work) 😌 Efficient and scalable graph reasoning (on commodity GPUs) enabled by good ole A* @zhu_zhaocheng and @XinyuYuan402 did a great job, follow them! latest arxiv:

3

0

34

0

11

Xinyu Yuan

@XinyuYuan402

10 months

Would be at #NeurIPS next week! Let’s chat about generalizations for relational graphs!!

Zhaocheng Zhu

@zhu_zhaocheng

10 months

🎊 At the year-end gala #NeurIPS . Let's discuss reasoning, LLM, KG & systems! We baked two dishes for inductive reasoning: one scales to million-scale KGs (Wed. 3-5pm) and the other generalizes to arbitrary KGs (Fri. GLFrontiers). w/ @michael_galkin @XinyuYuan402 @tangjianpku

0

18

0

15

Xinyu Yuan

@XinyuYuan402

11 months

📢📢📢

Michael Galkin

@michael_galkin

11 months

In our new Medium blog post with @XinyuYuan402 @zhu_zhaocheng and special guest @brunofmr we explore - the theory of inductive reasoning - foundation models for KGs - and explain our recent ULTRA in more detail!

1

14

73

0

10

Xinyu Yuan

@XinyuYuan402

10 months

@michael_galkin @HannesStaerk love the T-shirt!

0

3

Xinyu Yuan

@XinyuYuan402

2 years

#NewProfilePic

0

5

Xinyu Yuan

@XinyuYuan402

1 year

interesting design

0

3

Xinyu Yuan

@XinyuYuan402

11 months

Lab work!

Minghao Xu

@MinghaoXu_Alan

11 months

Check out our latest ESM-GearNet project! We conduct a systematical study on the architecture design and learning methods of protein structure-sequence joint representations 👯

0

6

0

4

Xinyu Yuan

@XinyuYuan402

2 years

So happy to see this: "With the recent upstreams of torch-scatter and torch-sparse to native PyTorch, we are happy to announce that any installation of the extension packages torch-scatter, torch-sparse, torch-cluster and torch-spline-conv is now fully optional"

PyG

@PyG_Team

2 years

Latest PyG 2.3 Release is now out! Learn more about the new features here:

1

16

52

0

3

Xinyu Yuan

@XinyuYuan402

10 months

@zhu_zhaocheng People always prioritize to chase what they don’t have now and have wanted the most, but realize later something lost or ignorant can then never be pursued back again, like health😅

1

0

1

Xinyu Yuan

@XinyuYuan402

9 months

@michael_galkin super super congrats on our paper!!

0

2

Xinyu Yuan

@XinyuYuan402

1 year

Finally out!🎉

Zhaocheng Zhu

@zhu_zhaocheng

1 year

Make ChatGPT more factual by equipping it with KG reasoning tools ⚒️ We release A*Net and integrate it with ChatGPT. A*Net is a scalable, inductive and interpretable path-based GNN on KGs. It is the first non-embedding method on the OGB leaderboard. 🧵1/6

4

32

149

0

1

Xinyu Yuan

@XinyuYuan402

1 year

(6/6) It also proves its efficacy in zero-shot protein classification and functional protein retrieval from a large-scale database.

1

0

1

Xinyu Yuan

@XinyuYuan402

1 year

This awesome project is led by @MinghaoXu_Alan and thank all the other collaborators @MiretSantiago and @tangjianpku !

0

1

Xinyu Yuan

@XinyuYuan402

1 year

(5/6) ProtST outperforms previous PLMs on diverse representation learning benchmarks.

0

1

Xinyu Yuan

@XinyuYuan402

1 year

(4/6) On downstream tasks, ProtST enables both supervised learning tasks and zero-shot prediction, utilizing the aligned representation space of protein sequences and textual descriptions. This versatility of ProtST opens new avenues in protein study and application.

0

1

Xinyu Yuan

@XinyuYuan402

1 year

@HannesStaerk @LogConference @chaitjo @DrBPChamberlain @mmbronstein @Pseudomanifold @YuanqiD The reviewer sign-up form is still open? I thought it was closed before June

1

0

1

Xinyu Yuan

@XinyuYuan402

1 year

@zhu_zhaocheng brain wave activity

0

1

Xinyu Yuan

@XinyuYuan402

1 year

@wangshengpkucn Hi Prof. Sheng, thank you for the comments. It’s a great work. I think it shares the same essential idea as our ProtST to bring two modality (protein sequences and functional descriptions) into an aligned space, which is the key to zero shot prediction.

0

1

Xinyu Yuan

@XinyuYuan402

1 year

@zdhnarsil enjoy the summer in a different way!

0

1