Jiaxuan You @youjiaxuan Twitter profile | Pikagi

Pikagi

Jiaxuan You

@youjiaxuan

1,704

Followers

157

Following

12

Media

73

Statuses

Incoming Assistant Prof #UIUC CS. Directing #ULab @IllinoisCS . Senior Research Scientist #NVIDIA #Stanford CS PhD

Palo Alto, CA

https://t.co/8qzXc78TLR

Joined April 2017

Don't wanna be here? Send us removal request.

Pinned Tweet

@youjiaxuan

Jiaxuan You

20 days

📚 Struggling to keep up with the latest research? Meet Arxiv Copilot, our automated tool that generates daily paper summaries tailored to your interests. Just input your name, and voilà! Curious about @ylecun 's take? You can explore that too 🚀 👉 Demo:

Tweet media one

Tweet media two

Tweet media three

1

21

113

Last Seen Profiles

@alanaparente

@Hyjinx_eSports

@filtergrade

@himedoufukaosu

@Tecrider1

@Samuel_Gregson

@artbees_design

@nikitobase

@Kingjem5

@smsakdibuy42056

@SocialDemSheff

@cinyc9

@immaculategrid

@CoachJP22

@YorkWallsFriend

@Autie_Radig

@FixerForYou

@saadounalotaibi

@HuskPowerSystem

@HEATSHOWYOO

@ItsDylanNorth

@OverLucidity

@FCB_PANDA

@Johnlab60

@schadenfreude74

@nikonislove

$طــــ/\ل.. CR7𓃵$

@talal0_v

@nan2000web

@Lordybar

@saltuncensored

@Starwalker12345

@lorenandre75

@yui_alter38598

@oscardelgado60

@fukumimasuzoi

@zenderem

@youjiaxuan

Jiaxuan You

4 years

We are excited to release #GraphGym , a platform for designing and evaluating #GraphNeuralNetworks . It provides a modularized pipeline, a system for launching thousands of experiments, and more! Code: Paper: #NeurIPS2020 Spotlight

Tweet card media

Design Space for Graph Neural Networks

The rapid evolution of Graph Neural Networks (GNNs) has led to a growing number of new architectures as well as novel applications. However, current research focuses on proposing and evaluating...

4

50

233

@youjiaxuan

Jiaxuan You

4 years

How does the graph structure of a neural network affect its predictive performance? Our ICML 2020 paper "Graph Structure of Neural Networks" reveals many interesting findings on this topic. with Jure Leskovec, Kaiming He, Saining Xie #ICML2020

Tweet card media

Graph Structure of Neural Networks

Neural networks are often represented as graphs of connections between neurons. However, despite their wide use, there is currently little understanding of the relationship between the graph...

3

32

230

@youjiaxuan

Jiaxuan You

1 month

🚀 Excited to announce "How Far Are We From AGI?", first paper summarizing current and future research directions toward #AGI . We hope it inspires researchers to achieve AGI responsibly as a #community . 📄 Paper: 💻 GitHub (PR🤗):

Tweet media one

Tweet media two

Tweet media three

Tweet media four

2

48

142

@youjiaxuan

Jiaxuan You

2 years

Excited to share our ICLR 2022 spotlight paper 😀 Relational Multi-Task Learning: Modeling Relations between Data and Tasks Our poster session is in an hour at 10:30am PT, Welcome to stop by! Paper: Poster:

Tweet media one

1

16

129

@youjiaxuan

Jiaxuan You

3 years

I am excited to announce that GraphGym has integrated with PyG in our latest PyG 2.0 release! Blog: For more info, come to hear my talk about GraphGym at the Stanford GNN workshop tomorrow! Event: YouTube:

Tweet media one

0

14

113

@youjiaxuan

Jiaxuan You

3 years

Great to be part of this! I'll present 2 talks: - GNN applications in financial networks - GraphGym: Easy-to-use Platform for Graph Learning I'll post the resources for the talks later. Welcome to attend the workshop on Sept 16!

@jure

Jure Leskovec

3 years

Stanford is proud to bring together leaders from academia&industry to showcase advances in Graph Neural Networks. Program includes applications, frameworks and industry panels on challenges of graph-based machine learning models. Register at:

Tweet media one

11

223

902

0

23

111

@youjiaxuan

Jiaxuan You

5 months

🚀Dive into the Future of AGI at the #ICLR2024 AGI Workshop (Hybrid mode in May)! Join our discussions on how far we are from AGI. Keynotes by the legendary Yoshua Bengio and other renowned speakers. Submit your work (7 or 9 pages) by Feb 9. Learn more:

Tweet media one

Tweet media two

Tweet media three

4

19

100

@youjiaxuan

Jiaxuan You

10 months

🚀 Thrilled to announce the 2nd GLFrontiers Workshop at NeurIPS 2023! Following the success of our 1st workshop, we're eager to explore Foundation Models for Graphs, Graphs + LLMs, Graph AI for Science, and more! Submit your groundbreaking research now!

Call for Papers

NeurIPS Workshop

glfrontiers.github.io

2

14

81

@youjiaxuan

Jiaxuan You

1 month

ICLR folks - Join our discussions on #AGI at the #ICLR2024 #AGIWorkshop on May 11 (Sat)! Keynotes from renowned speakers: Yoshua Bengio, @OriolVinyalsML , @YejinChoinka , @andrewgwils , @songhan_mit , and @AISafetyInst , followed by panel discussion. Website:

Tweet media one

Tweet media two

2

15

85

@youjiaxuan

Jiaxuan You

6 months

🚀Join us tomorrow (Dec 15) at NeurIPS GLFrontiers Workshop from 8:45 am in Hall C2! Explore the latest in Graphs, LLMs, RAGs, AI for Science, and more! Keynotes from UIUC, Harvard, NVIDIA, Deepmind, plus panel discussions. A day packed with cutting-edge research and networking!

Tweet media one

Tweet media two

0

6

44

@youjiaxuan

Jiaxuan You

4 years

We have just open sourced the code for "Graph Structure of Neural Networks"! It should be pretty clean and easy to use :) Code: Paper: Slides: with Jure Leskovec, Kaiming He, Saining Xie, ICML 2020

GitHub - facebookresearch/graph2nn: code for paper "Graph Structure of Neural Networks"

code for paper "Graph Structure of Neural Networks" - facebookresearch/graph2nn

0

4

35

@youjiaxuan

Jiaxuan You

23 days

This groundbreaking work on discrete generation could revolutionize the creation of text, graphs, and biological structures. It may signal a new direction for LLMs, utilizing flow matching instead of traditional auto-regressive modeling. Exciting to see the progress! #AI #LLM

@GeLiuSaber

Ge Liu

23 days

1/4 Can we unleash the power of continuous Riemannian Flow Matching on discrete generation? We introduce “Statistical Flow Matching (SFM)”, a novel FM framework on the manifold of probability measures inspired by information geometry. Kudos to @ccr_cheng

3

30

237

0

1

30

@youjiaxuan

Jiaxuan You

5 years

I'm going to present our paper "Position-aware Graph Neural Networks" (P-GNNs) in ICML today. I have a 20 min talk (4:00-4:20, Room 102) and poster tonight. Welcome to attend! Paper: Code:

Tweet media one

0

5

27

@youjiaxuan

Jiaxuan You

4 years

In our #NeurIPS2020 paper, we propose GRAPE as a general framework for the missing data problem, including both feature imputation and label prediction aspects. Our key innovation is to solve the problem with graph representation. Paper:

Tweet media one

1

3

26

@youjiaxuan

Jiaxuan You

4 months

🚀Submit your work to #ICLR2024 AGI Workshop! Join our discussions on how far we are from AGI. Preliminary works, or papers unfortunately rejected by ICLR, are also highly welcomed! We have extended our submission deadline to Feb 11 (AOE). #AGI Learn more:

@youjiaxuan

Jiaxuan You

5 months

🚀Dive into the Future of AGI at the #ICLR2024 AGI Workshop (Hybrid mode in May)! Join our discussions on how far we are from AGI. Keynotes by the legendary Yoshua Bengio and other renowned speakers. Submit your work (7 or 9 pages) by Feb 9. Learn more:

Tweet media one

Tweet media two

Tweet media three

4

19

100

0

3

23

@youjiaxuan

Jiaxuan You

4 years

Our poster session #NeurIPS2020 is happening in 20 mins! "Design Space for Graph Neural Networks" Poster link: Paper: Code (GraphGym):

Tweet card media

GitHub - snap-stanford/GraphGym: Platform for designing and evaluating Graph Neural Networks (GNN)

Platform for designing and evaluating Graph Neural Networks (GNN) - snap-stanford/GraphGym

@youjiaxuan

Jiaxuan You

4 years

We are excited to release #GraphGym , a platform for designing and evaluating #GraphNeuralNetworks . It provides a modularized pipeline, a system for launching thousands of experiments, and more! Code: Paper: #NeurIPS2020 Spotlight

4

50

233

0

3

20

@youjiaxuan

Jiaxuan You

2 years

Excited to organize the NeurIPS 2022 GLFrontiers Workshop with the amazing organizers: @marinkazitnik @RexYing0923 @YizhouSun @hanjundai @StefanieJegelka Your submissions are highly welcomed! Please stay tuned to our official website:

New Frontiers in Graph Learning (GLFrontiers)

NeurIPS Workshop

glfrontiers.github.io

@glfrontiers

Graph Learning Frontiers

2 years

New Frontiers in Graph Learning Workshop at NeurIPS 2022 @NeurIPSConf is official! Our website for more info: Submission site: Our amazing organizers: @youjiaxuan @marinkazitnik @RexYing0923 @YizhouSun @hanjundai @StefanieJegelka

1

16

75

0

2

19

@youjiaxuan

Jiaxuan You

3 years

We are excited to release PyG 2.0, and a brand-new homepage ! It's amazing to be part of the PyG team. Congrats on all the hard work over the past few months!

Tweet card media

PyG is the ultimate library for Graph Neural Networks

@jure

Jure Leskovec

3 years

We are excited to announce PyG <>, a major new release of Pytorch Geometric-- a collaboration between Stanford and TU Dortmund. To learn more about PyG come to the Stanford Graph Learning workshop:

Tweet media one

0

69

392

0

3

16

@youjiaxuan

Jiaxuan You

2 years

Our NeurIPS 2022 GLFrontiers Workshop, presenting the new frontiers of graph learning, will be happening tomorrow (Dec 2nd)! We have an exciting program - looking forward to seeing you there! You may attend in person or watch live virtually. More info:

1

3

9

@youjiaxuan

Jiaxuan You

3 years

This year's CS224W is fully redesigned. We introduce many cutting-edge ML technologies for graphs. Enjoy the course! Syllabus: YouTube playlist:

Tweet card media

Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 1.1 -...

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3Bu1w3nJure LeskovecComputer Sci...

www.youtube.com

@jure

Jure Leskovec

3 years

By popular demand we are releasing lecture videos for Stanford CS224W Machine Learning with Graphs which focuses on graph representation learning. Two new lectures every week. Videos: Syllabus:

Tweet media one

32

777

3K

0

3

8

@youjiaxuan

Jiaxuan You

1 month

We sincerely appreciate the successful organization of the ICLR 2024 AGI Workshop, the most popular workshop at ICLR with 800+ attendees. Keynotes by Yoshua Bengio, Oriol Vinyals, Yejin Choi, Andrew G Wilson, and Song Han are summarized in our paper. Web:

Tweet media one

Tweet media two

0

1

9

@youjiaxuan

Jiaxuan You

2 years

Submission DDL for our NeurIPS 2022 New Frontiers in Graph Learning (GLFrontiers) Workshop has been extended to Sept 22. Looking forward to your submissions! CFP:

@youjiaxuan

Jiaxuan You

2 years

Excited to organize the NeurIPS 2022 GLFrontiers Workshop with the amazing organizers: @marinkazitnik @RexYing0923 @YizhouSun @hanjundai @StefanieJegelka Your submissions are highly welcomed! Please stay tuned to our official website:

0

2

19

0

1

6

@youjiaxuan

Jiaxuan You

9 months

📆2 days left! Submit your groundbreaking ML research to the 2nd GLFrontiers Workshop at NeurIPS 2023. Let's dive into Foundation Models for Graphs, Graphs + LLMs, Graph AI for Science, and more! Don't miss out! CFP: #GLFrontiers #NeurIPS #LLMs

Call for Papers

NeurIPS Workshop

glfrontiers.github.io

1

0

6

@youjiaxuan

Jiaxuan You

8 months

Demo video credit: Zizhao Zhang

0

0

3

@youjiaxuan

Jiaxuan You

5 months

Thanks to the amazing co-organizers!! @GeLiuSaber @YunzhuLiYZ @songhan_mit @dawnsongtweets

0

0

4

@youjiaxuan

Jiaxuan You

6 years

We've released our code for GraphRNN, feel free to try it out!

Tweet card media

GitHub - JiaxuanYou/graph-generation: GraphRNN: Generating Realistic Graphs with Deep Auto-regres...

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models - JiaxuanYou/graph-generation

1

2

4

@youjiaxuan

Jiaxuan You

20 days

Our goal is to accelerate the spread of scientific knowledge with Arxiv Copilot. Currently a proof-of-concept, we welcome your feedback and contributions! ⭐ Star us on Huggingface if you find it useful. Kudos to #ULab members: Guanyu Lin, Tao Feng, Barry Han. #AI #Arxiv #Science

0

0

4

@youjiaxuan

Jiaxuan You

4 years

Our ICML booth We will present on July 16 7am and 8pm PDT

0

0

3

@youjiaxuan

Jiaxuan You

8 days

@YunzhuLiYZ @ColumbiaCompSci Congrats Yunzhu!

0

0

2

@youjiaxuan

Jiaxuan You

6 years

Our paper is the first Graph Generative Model that can scale to hundreds of nodes, and achieves amazing results in various graph datasets. We also propose a MMD based evaluation method for graph generation.

@arxiv_org

arxiv

6 years

GraphRNN: A Deep Generative Model for Graphs.

Tweet media one

Tweet media two

Tweet media three

Tweet media four

3

49

122

0

1

2

@youjiaxuan

Jiaxuan You

4 years

Project website:

1

0

2

@youjiaxuan

Jiaxuan You

10 months

Thanks to the amazing co-organizers: @RexYing0923 @hanjundai @GeLiu84987396 @Azaliamirh @smitakrishnaswa

1

0

1

@youjiaxuan

Jiaxuan You

4 years

@ChaykowskyMike Thanks for the suggestion! You can register these layers in "/graphgym/contrib/layer/", following the examples there. We currently don't have official implementation but we'll consider adding it.

0

0

1

@youjiaxuan

Jiaxuan You

4 years

@ajaydiv It's great to hear that! Thank you!

0

0

1

@youjiaxuan

Jiaxuan You

8 months

@labloke11 DBGym views the database (including multiple tables) as a whole, and fully utilizes all the relevant information to make predictions regarding a given column. The idea is to leverage primary-foreign key linkages to implicitly connect tables together, without explicit table join.

0

0

0

@youjiaxuan

Jiaxuan You

2 years

Excited to organize the NeurIPS 2022 GLFrontiers Workshop with the amazing organizers: @marinkazitnik @RexYing0923 @YizhouSun @hanjundai @StefanieJegelka

0

0

1

@youjiaxuan

Jiaxuan You

4 years

@Deep__AI We are excited to release #GraphGym , a platform for designing and evaluating #GraphNeuralNetworks . It provides a modularized pipeline, a system for launching thousands of experiments, and more! Code: Paper: #NeurIPS2020 Spotlight

Tweet card media

Design Space for Graph Neural Networks

The rapid evolution of Graph Neural Networks (GNNs) has led to a growing number of new architectures as well as novel applications. However, current research focuses on proposing and evaluating...

0

0

1

@youjiaxuan

Jiaxuan You

6 years

Hello Twitter! #myfirstTweet

Tweet media one

0

0

1