Rose Yu @yuqirose Twitter profile

Last Seen Profiles

@donngker

@ElizaPetch

@_Likybo

@HydeFanSite

@ZEBITEX

@TheLoveSchoolTV

@DiaperedPlanner

@LuvWickkk

@RealChrisCal

@z411127

@AngryMinis

@KondangAta58474

@bizarreID

@xgth_7

@nemethd

@DazzaBeeeee

@jandakembangstw

@bluebellrailway

@CloverhillFoods

@renaetoyou

@Coach_Nqo

@whitecinequinto

@AutorobotExpo

@indicatiu

@beaucolburn

@accuracy

@JT__Tackett

@SamanthaH_RN

@honami_DM

@Showing_Porns

@jandakembangstw

@ItsEBT_

@chespinthings

@HollywoodBowl

@Naeemullahkhan_

@tiffanyaws

Rose Yu

@yuqirose

1 month

📢 It is official! I got tenure!!!

154

14

2K

Rose Yu

@yuqirose

1 year

Many local minima in Deep Networks are connected through low-loss valleys. Curious about the theoretical origin of such valleys? Check out our #ICLR2023 Paper on #symmetry , local minima and conserved quantities. Paper: (1/3)

7

119

744

Rose Yu

@yuqirose

4 years

I have some exciting news to share. After spending some wonderful years at Northeastern, I will be joining @ucsd_cse at @UCSanDiego as an Assistant Professor in July 2020. I want to thank all my mentors for their support, and for folks at UCSD for making this happen.

51

8

430

Rose Yu

@yuqirose

2 years

Want to design #DeepLearning models that can generalize across dynamics? Check out our #NeurIPS2022 paper on ``Meta-Learning Dynamics Forecasting''. Paper: Code: (1/3)

8

77

424

Rose Yu

@yuqirose

2 years

It is official now! Very honored to receive the @NSF #CAREER award to investigate the frontiers of large-scale #spatiotemporal data!

45

6

419

Rose Yu

@yuqirose

7 months

How to design Diffusion Models for spatiotemporal forecasting? Check out our #NeurIPS2023 Paper on ``DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting''! Paper: Code: (1/3)

1

59

409

Rose Yu

@yuqirose

3 months

How does symmetry in #NeuralNetworks parameters impact learning? Check out our #ICLR2024 🔥spotlight🔥 paper on ``Improving Convergence and Generalization using Parameter Symmetries'' Paper: (1/3)

1

54

389

Rose Yu

@yuqirose

6 months

Love this thread. I also have to miss #NeurIPS2023 this year. Here is a flash back from my first @NeurIPSConf in 2014. Fan girl moment with @ylecun @geoffreyhinton 🤩!

Petar Veličković

@PetarV_93

6 months

I'm not at NeurIPS this year but I strongly echo this sentiment! 🥳 My very first NeurIPS (2017, Long Beach) was also the 1st anniversary of the Deep Learning book! And I got this awesome chance to candidly chat with @goodfellow_ian @AaronCourville and Yoshua Bengio.

1

4

106

4

10

363

Rose Yu

@yuqirose

4 years

I will be taking #PhD students in Fall 2021 at @UCSanDiego @ucsd_cse (Deadline Dec 16, no GRE required). Come to the beautiful La Jolla to work with us on #Physics -Guided #AI , #spatiotemporal #ML , #Tensor methods, and more! Grateful for RT!

4

115

319

Rose Yu

@yuqirose

3 years

Haha. Twitter beats me. Very excited about this work, to appear at #NeurIPS2021 ! Existing equivariant NNs require prior knowledge of the symmetry group. We propose the Lie algebra convolutional network (L-conv) that can automatically discover symmetries from data. (1/3)

andrea panizza

@unsorsodicorda

3 years

Interesting paper on automatic symmetry discovery for CNN by @nimatabari @RobinSFWalters @YanchenLiu13 @dashunwang @yuqirose using Lie algebras in place of Lie groups, you can discover continuous symmetries from data instead of assuming them!

2

9

58

4

51

319

Rose Yu

@yuqirose

1 year

We showed that simple dense models can outperform Transformers in #TimeSeries #forecasting . A great collaboration with @GoogleAI !

Google AI

@GoogleAI

1 year

Presenting TiDE, a time-series dense encoder for long-term time-series forecasting that enjoys the simplicity and speed of linear models while also being able to handle covariates and non-linear dependencies. Learn more →

30

270

1K

7

52

319

Rose Yu

@yuqirose

7 months

We all know Auto-Diff is easy in #DeepLearning , how about automatic integration? See our #NeurIPS2023 paper ``Automatic Integration for Spatiotemporal Neural Point Processes''. Paper: Code: (1/3)

4

49

300

Rose Yu

@yuqirose

3 years

New #ICLR2021 paper on Equivariant Continous Convolution for Trajectory Prediction. We leverage insights from #FluidDnamics to consider the internal symmetry in real-world trajectories. Paper: Code: (1/3)

4

52

262

Rose Yu

@yuqirose

2 years

How can #symmetry help optimization in #DeepLearning ? Check out our #NeurIPS2022 paper on ``Symmetry Teleportation for Accelerated Optimization''. Paper: (1/3)

8

46

253

Rose Yu

@yuqirose

1 year

Scientific simulations often run at multiple fidelity. How to best combine these data in high-dimensions? See our #ICML2023 paper on #Deep Bayesian Active Learning. Paper: Code: (1/3)

8

55

244

Rose Yu

@yuqirose

3 years

Our group is hiring PhD students in Spatiotemporal #MachineLearning , Physics-Guided #AI . Come to the beautiful La Jolla and work with us!!!

Arun Kumar

@TweetAtAKK

3 years

Academic applications season has begun! So, a pic of just another normal day in La Jolla I took on my way home from a workout. 😇 #AcademicLife #IsThisPropaganda ?🤔🤷‍♂️😂

1

107

5

44

237

Rose Yu

@yuqirose

4 years

Super honored to receive the award! Looking forward to more exciting research on #Physics -Guided #AI .

Google AI

@GoogleAI

4 years

Congratulations to the recipients of the 2019 Google Faculty Research Awards! We received over 900 proposals from universities worldwide, covering diverse research areas such as #MachineLearning , #HumanComputerInteraction , #DistributedComputing and more.

11

139

660

16

18

235

Rose Yu

@yuqirose

1 year

How to design #DeepLearning method that is robust against temporal distribution shift? Check out our #ICLR2023 paper on Koopman Neural Forecaster (KNF). Paper: Code: (1/3)

2

49

220

Rose Yu

@yuqirose

4 years

I am looking to hire postdocs at @ucsd_cse @UCSDJacobs in #MachineLearning and #Spatiotemporal modeling. Details. Grateful for RT!

2

117

216

Rose Yu

@yuqirose

1 year

How can #GenerativeAI help scientists discover symmetry from data? Check out our #ICML2023 paper on ``Generative Adversarial Symmetry Discovery''. Paper: Code: (1/3)

3

42

195

Rose Yu

@yuqirose

5 years

Two papers accepted in #Neurips2019 ! - NAOMI: Non-Autoregressive Multiresolution Sequence Imputation - Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology Thanks to amazing collaborators!

Understanding the Representation Power of Graph Neural Networks in...

To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a key property of...

arxiv.org

6

12

185

Rose Yu

@yuqirose

2 years

Poster session today!

Rose Yu

@yuqirose

3 years

Haha. Twitter beats me. Very excited about this work, to appear at #NeurIPS2021 ! Existing equivariant NNs require prior knowledge of the symmetry group. We propose the Lie algebra convolutional network (L-conv) that can automatically discover symmetries from data. (1/3)

4

51

319

7

21

166

Rose Yu

@yuqirose

3 years

Honored to receive the research award from @facebookai on sample-efficient sequential #decisionmaking ! #AI #ML

Announcing the winners of the Sample-Efficient Sequential Bayesian Decision Making request for...

In February 2021, Facebook launched a request for proposals (RFP) on sample-efficient sequential Bayesian decision-making. Today, we’re announcing the winners...

research.facebook.com

18

5

167

Rose Yu

@yuqirose

6 months

Interested in #DiffusionModel for spatiotemporal dynamics? Drop by our poster at Great Hall & Hall B1+B2 (level 1) #612 now! #NeurIPS2013

Rose Yu

@yuqirose

7 months

How to design Diffusion Models for spatiotemporal forecasting? Check out our #NeurIPS2023 Paper on ``DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting''! Paper: Code: (1/3)

1

59

409

0

26

151

Rose Yu

@yuqirose

3 years

If you are looking for #postdoc positions, apply to the @ucsd_cse CSE Fellows Program! Join us in the beautiful La Jolla! (Email me if you work on #ML #AI ) Deadline July 30, 2021.

3

45

143

Rose Yu

@yuqirose

4 years

New Paper on #Physics -Guided #DeepLearning for Turbulent Flow Prediction, to appear at #KDD2020 ! Blogpost: Paper: Code: (1/3)

2

29

137

Rose Yu

@yuqirose

3 years

Can I get some advice on how to deal with this #NeurIPS ? When all 4 reviewers give acc/strong acc for your submission, and the AC jumps in 1 day before the discussion period and pushes strongly against all reviews. I thought paper review is a democratic process?

13

8

136

Rose Yu

@yuqirose

2 years

Join this great tutorial by @cosmo_shirley and @MilesCranmer on #ML and #Physics @NeurIPSConf #NeurIPS2021 ! --- Moderated by @wellingmax and myself.

NeurIPS Conference

@NeurIPSConf

3 years

#NeurIPS2021 Tutorials: Shirley Ho @cosmo_shirley (Flatiron Institute, NYU, Princeton University) and Miles Cranmer @MilesCranmer (Princeton University), will be giving a tutorial on “ML for Physics and Physics for ML”. Dec 6, 17:00-21:00 (GMT)

2

45

218

2

12

128

Rose Yu

@yuqirose

3 months

How to properly quantify uncertainty for multi-step sequence prediction? Check out our #ICLR2024 paper on ``Copula Conformal prediction for Time Series Forecasting''. Paper: Code: (1/3)

4

17

124

Rose Yu

@yuqirose

10 months

Interested in learning #deeplearning surrogate models for stochastic physics simulator? Check out our #KDD2023 paper on ‘Deep Bayesian Active Learning for Accelerating Stochastic Simulations’! Paper: Code: (1/3)

2

23

124

Rose Yu

@yuqirose

3 years

New faculty dinner with our awesome colleagues and chair! @ucsd_cse @UCSDJacobs

0

118

Rose Yu

@yuqirose

3 years

Honored to be a featured speaker at @nvidia #GTC21 for "Physics-Guided #DeepLearning for #FluidDynamics " on Wednesday, April, 14th at 8:00am PDT (11 am EDT). Free Registration at

2

11

118

Rose Yu

@yuqirose

3 years

Submit to #ICLR2021 workshop on #DeepLearning for #Simulation , organized by @jure @PeterWBattaglia @ryan_p_adams and myself. Would love to see your best work on #Physics -Guided #DeepLearning !!!

Deep Learning for Simulation (SimDL)

ICLR 2021 Workshop

simdl.github.io

1

18

110

Rose Yu

@yuqirose

4 years

Want to improve the generalization of #DeepLearning for #TimeSeries prediction? Check out our new paper on incorporating #symmetries into deep dynamics models Led by awesome @Rayw1521 and postdoc @Northeastern

2

23

106

Rose Yu

@yuqirose

1 month

How to design Transformers to discover Granger causality from event sequence? Check out our paper at @aistats_conf 2024. (1/3)

4

10

102

Rose Yu

@yuqirose

3 years

I feel extremely fortunate to be leading the @ENERGY project on Scientific #MachineLearning with @PierreGentine @s_mandt on #AI for #Climate . DOE News: Award Details:

Department of Energy Invests $16 Million in Data-Intensive Scientific Machine Learning Research and...

The U.S. Department of Energy (DOE) announced $16 million for five collaborative research projects to develop artificial intelligence (AI) and machine learning (ML) algorithms.

www.energy.gov

4

100

Rose Yu

@yuqirose

1 year

Congratulations to Dr. Rui (Ray) Wang @Rayruw on his awesome PhD thesis defense in @ucsd_cse ! Ray spearheaded the area of #Physics -Guided #DeepLearning for dynamical forecasting!

1

98

Rose Yu

@yuqirose

9 months

Are you excited about #AI for #Science ? We are hiring a postdoc on #DeepLearning for #fusion to start ASAP, in collaboration with @GeneralAtomics , see below for details. It was eye-opening to visit the GA lab in San Diego. Appreciate repost!

3

18

86

Rose Yu

@yuqirose

3 years

First group social at @UCSanDiego

1

0

89

Rose Yu

@yuqirose

1 year

Extremely honored to speak among those distinguished speakers !!! Thanks to the organizers for the invitation! #MachineLearning #Physics -Guided #AI

L4DC Conference

@l4dc_conf

1 year

Thrilled to announce our 🔥 Keynote Speakers 🔥 for L4DC 2023: @ylecun @yuqirose @robo_kween @vikassindhwani Aaron Ames ( @AMBER_lab ) and Tamer Başar!

0

11

99

1

3

86

Rose Yu

@yuqirose

2 years

Just arrived at #NeurIPS2022 ! I will be here for a week. Look forward to meeting old and new friends! Come by our talks and posters!

1

5

83

Rose Yu

@yuqirose

4 years

Excited to attend #NeurIPS2019 ! I will be at - @WiMLworkshop mentoring topic #35 - Wed poster #147 - Thur poster # 37 - Talk at ML4PS () Let's talk if you are interested in #Spatiotemporal #Graph #Physics -Guided #AI , #Women in #ML or good food :)

2

79

Rose Yu

@yuqirose

2 years

It’s an interesting feeling to experience an #earthquake while writing a paper…like we are rocking it ???

3

1

79

Rose Yu

@yuqirose

4 years

Given all the sentiments around #NeurIPS2020 , it might be a good time to revisit the famous experiment @mrtz To students: #MachineLearning conference acceptances are more random than we had previously realized. Let us focus on doing good science!

1

4

77

Rose Yu

@yuqirose

1 year

Very excited about this event on #AI4Science @UCSanDiego . UCSD communities are welcome! Look forward to the talks by @WillettBecca @cosmo_shirley @adityagrover_ , Thanks to the generous sponsorship from @ucsd_cse @HDSIUCSD @Scripps_Ocean !

Ucsdmics

@ucsdmics

1 year

Join MICS faculty @yuqirose & Yuanyuan Shi at the launching event of the AI & Science series - Scientific ML Symposium on March 17! Details & registration at:

0

2

7

2

9

75

Rose Yu

@yuqirose

6 months

I have to miss #NeurIPS2023 😢. But my students and collaborators will be there🥳! @salvaRC7 @ZihaoKevinZhou @BoZhao__ @RobinSFWalters @nimatabari We are actively recruiting students and postdocs in #Physics -Guided #AI , #generativeAI , among others! Pls DM/email if interested!

1

4

73

Rose Yu

@yuqirose

3 years

We appreciate the generous support from @ENERGY ! Excited to work on #Spatiotemporal #ML , #AI for #Climate , @HDSIUCSD @UCSDJacobs

UCSD CSE

@ucsd_cse

3 years

CSE Assistant Professor Rose Yu @yuqirose is the lead investigator on a new Department of Energy project to develop machine learning methods to understand climate data. Congratulations! Read more here:

2

3

40

6

1

69

Rose Yu

@yuqirose

3 years

My first in-person conference since the pandemic. So excited to be speaking with all the amazing people! #MachineLearning #Climate @eigensteve @laurezanna

Kavli Institute for Theoretical Physics

@KITP_UCSB

3 years

The Machine Learning for Climate conference starts today at 9 am PDT! KITP's #CLIMATE -C21 conference will be in Kohn Hall's Fred Kavli Auditorium and on Zoom this week from November 1-4. More info: Stay tuned for recorded talks:

0

9

23

3

6

66

Rose Yu

@yuqirose

3 years

Very proud of @Rayruw for winning the #Best Paper Award at #MachineLearning for #PublicHealth @NeurIPSConf . In collaboration with @LoVVgE @bear5claw from @AmazonScience Announcement: Full paper:

Bridging Physics-based and Data-driven modeling for Learning...

How can we learn a dynamical system to make forecasts, when some variables are unobserved? For instance, in COVID-19, we want to forecast the number of infected and death cases but we do not know...

arxiv.org

5

3

66

Rose Yu

@yuqirose

2 years

Postdoc positions in Data-Intensive Scientific #MachineLearning , hosted at @UCSanDiego @Columbia @UCIrvine #AI #Jobs Apply to work with our amazing team including @eliasbareinboim @PierreGentine @s_mandt @Pritchard_UCI , among others!

3

22

62

Rose Yu

@yuqirose

2 years

Fun academic family reunion. Thank you for visiting us @yisongyue and talk about your amazing work!

0

1

60

Rose Yu

@yuqirose

6 years

For people interested in physics+machine learning, check out this conference that I'm co-coordinating. . Thanks to Miles Stoudenmire for inviting me. Though I'm probably the one who knows the least about theoretical physics among others ...

0

29

61

Rose Yu

@yuqirose

4 years

I don't understand why there are so many announcements about X number of papers accepted to #NeurIPS2020 . Don't we need to adopt reviewers/meta reviewer's suggestions, clean up and open-source the code, and prepare camera-ready? #MachineLearning

5

2

60

Rose Yu

@yuqirose

5 months

Very proud that our superstar undergrad Peter Eckmann () was selected as a Finalist of the 2023-2024 Outstanding Undergraduate Researcher Award ( )! Peter does amazing work on #AI for #DrugDiscovery .

Outstanding Undergraduate Researcher Award

Recognizes undergraduate students in North American universities who show outstanding research potential in an area of computing research.

cra.org

3

61

Rose Yu

@yuqirose

4 years

We establish theoretical limits for source identification in epidemic models, with empirical analysis on various dynamics including COVID-19.

NetScience

@net_science

4 years

Latest out. "Finding Patient Zero: Learning Contagion Source with Graph Neural Networks". Great collaboration with @_chnsh_ @nimatabari @mattk7 @barabasi @alexvespi @yuqirose

4

73

151

2

9

60

Rose Yu

@yuqirose

3 years

Excited to give a tutorial with @ParisPerdikaris @anujkarpatne at @kdd_news tmr at 13:00 PT about #Physics -Guided #AI for #Spatiotemporal Data! Website: RSVP:

Home

sites.google.com

1

16

61

Rose Yu

@yuqirose

1 year

I am honored to be part of the faculty cohort @UCSDJacobs . We met at faculty housing and have formed a strong friendship since we started. Now the friendship has turned into exciting research collaborations!

UCSD Engineering

@UCSDJacobs

1 year

Congrats to the 6 @UCSDJacobs faculty + their students who launched lab-to-lab research collaborations via the Jacobs School Early Career Faculty Development Award @BrianAguado and @LPoulikakos @Dr_PatyHG and @yuanyuanYYShi @Zjahed and @yuqirose

0

4

24

3

0

60

Rose Yu

@yuqirose

5 years

New results on understanding graph neural network in learning graph topology at #NeurIPS2019 ! Paper Code (1/4)

GitHub - nimadehmamy/Understanding-GCN: code for the paper in NeurIPS 2019

code for the paper in NeurIPS 2019 . Contribute to nimadehmamy/Understanding-GCN development by creating an account on GitHub.

github.com

1

7

56

Rose Yu

@yuqirose

4 years

New paper on Efficient and Interpretable Spatial Data Analysis with Multiresolution #Tensor #Learning to appear at #ICML2020 Paper: Code: (1/3)

GitHub - Rose-STL-Lab/mrtl: Multiresolution Tensor Learning

Multiresolution Tensor Learning. Contribute to Rose-STL-Lab/mrtl development by creating an account on GitHub.

github.com

1

12

55

Rose Yu

@yuqirose

1 year

The #AI4Science symposium was a blast! Thanks to all the speakers @WillettBecca @cosmo_shirley @DWatsonParris and organizers @SciPritchard @eliasbareinboim @PierreGentine @mvanlierwalq @Nick_Lutsko ! Sponsored by @ucsd_cse @HDSIUCSD @Scripps_Ocean #MachineLearning #Climate

Rose Yu

@yuqirose

1 year

The event is TODAY at Great Hall!

0

1

15

3

53

Rose Yu

@yuqirose

3 years

New #KDD2021 paper on Uncertainty Quantification (UQ) in Deep #Spatiotemporal forecasting. Paper: Code: Presentation: Aug 16 at 1 pm PST (Oral R-20) (1/3)

1

11

52

Rose Yu

@yuqirose

4 years

New paper on ``Learning Disentangled Representations of Video with Missing Data '', To appear at #NeurIPS2020 . Paper: Code: (1/4)

GitHub - Rose-STL-Lab/DIVE: Disentangled Imputed Video autoEncoder (DIVE)

Disentangled Imputed Video autoEncoder (DIVE) . Contribute to Rose-STL-Lab/DIVE development by creating an account on GitHub.

github.com

2

4

52

Rose Yu

@yuqirose

6 years

I am furious to find out about Uber's @UberEng false claim on their #ICML #TimeSeries workshop . Researchers spent a lot of effort organizing workshops. In fact, they even misspelt ICML as ''International Machine Learning Convention''...

Engineering Extreme Event Forecasting at Uber with Recurrent Neural Networks | Uber Blog

Recurrent neural networks equip Uber Engineering's new forecasting model to more accurately predict rider demand during extreme events.

www.uber.com

3

15

51

Rose Yu

@yuqirose

4 months

Another example from #Sora of why we need #physics -guided #AI Yes. It is fun to watch soft simulations but it would be difficult to use them in high-stakes science and engineering applications. See use cases in our DYffusion paper.

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

We introduce a novel diffusion model-based framework, DYffusion, for large-scale probabilistic forecasting. We propose to couple the diffusion steps with the physical timesteps of the data, leading...

ucsdml.github.io

Jim Fan

@DrJimFan

4 months

I see some vocal objections: "Sora is not learning physics, it's just manipulating pixels in 2D". I respectfully disagree with this reductionist view. It's similar to saying "GPT-4 doesn't learn coding, it's just sampling strings". Well, what transformers do is just manipulating

252

460

3K

0

2

51

Rose Yu

@yuqirose

10 months

Reunion with PhD advisor @yanliu_usc and our labs @kdd_news ! #KDD2023 #AcademicFamily .

0

2

50

Rose Yu

@yuqirose

4 years

For those who will have completed a Ph.D. from a U.S. institution between Jan 1, 2018, and Dec 31, 2020, and are looking for a job: Contact me if you are into #Physics -Guided #AI , #ML for #Spatiotemporal Data.

0

14

48

Rose Yu

@yuqirose

2 years

Group lunch at #NeurIPS2022 with distinguished guests @shakir_za @yanliu_usc ☺️It was lovely catching up and meeting people after so long!

1

0

49

Rose Yu

@yuqirose

3 years

Honored to receive the @AmazonScience #MachineLearning Research award! Thanks for the support!

2

1

47

Rose Yu

@yuqirose

2 years

Flying to Stanford for @l4dc2022 ! Look forward to meeting old and new friends!

Rose Yu

@yuqirose

2 years

New paper to appear at #L4DC2022 on Neural Point Process for modeling irregularly sampled event data over space and time. (1/3) #DeepLearning #AI Paper: Code:

2

3

39

1

4

48

Rose Yu

@yuqirose

5 years

Come to our poster by @claradepaolis at #neurips2018 relational representation learning #R2L workshop on neural programming DAG-to-DAG translation at 4:45 pm

0

14

47

Rose Yu

@yuqirose

3 years

New #ICLR2021 paper on Incorporating Symmetry in Deep Dynamics model. We study symmetry in Differential Equations, applied to #TurbulentFlow and #OceanCurrent . Paper: Code: (1/3)

2

9

46

Rose Yu

@yuqirose

3 years

Jokes aside, (promoting the rejected 8,6,7 paper) Let me share our accepted papers to #ICLR2021 . Work led by amazing postdoc @RobinSFWalters and Ph.D. student @Rayruw on #Physics -Guided #DeepLearning and #Spatiotemporal #ML . (1/2)

1

3

48

Rose Yu

@yuqirose

2 years

Look forward to presenting the keynote talk at #KDD2022 , workshop on #Climate and #Physics -Guided #DeepLearning !

Fragile Earth 2022 - AI for Good Foundation

Fragile Earth 2022: AI for Climate Mitigation, Adaptation, and Environmental Justice workshop. Learn more...

ai4good.org

1

6

45

Rose Yu

@yuqirose

10 months

I will be at #KDD2023 tomorrow, giving two keynote talks 1. Uncertainty Reasoning and Quantification () 2. Data Science for Social Good () In addition to our paper presentations by talented students @allen_dongxiawu and Brooks Niu!

Data Science for Social Good at KDD 2023

In this workshop, we invite the research community in data science for social good to submit papers for DSSG workshop at KDD 23.

kdd-dssg.github.io

1

0

46

Rose Yu

@yuqirose

3 years

Apply and join our lab to work on #Physics -Guided #MachineLearning with applications to #Climate #Healthcare and #PhysicalSciences !

1

16

46

Rose Yu

@yuqirose

3 years

Time Series Workshop #ICML2021 today! #TSW2021 .

1

4

44

Rose Yu

@yuqirose

6 months

Interested in learning about Automatic Integration in #DeepLearning ? Drop by our poster now at Great Hall & Hall B1+B2 (level 1) #816 !

Rose Yu

@yuqirose

7 months

We all know Auto-Diff is easy in #DeepLearning , how about automatic integration? See our #NeurIPS2023 paper ``Automatic Integration for Spatiotemporal Neural Point Processes''. Paper: Code: (1/3)

4

49

300

2

3

43

Rose Yu

@yuqirose

5 years

Excited to give a talk at #NVIDIA #GTC19 tomorrow morning at 9 am about " #DeepLearning For #Spatiotemporal Data". Come join me for a deep dive into space and time!

1

5

41

Rose Yu

@yuqirose

4 years

Tune in on Nov 13/14 on #physics -guided #AI for Scientific Discovery @RealAAAI Honored to speak together with @tegmark @eigensteve @vagelispapalex @AnimaAnandkumar and many others! Thanks to organizing committee @anujkarpatne @yanliu_usc

PGAI-AAAI-20

Register for this symposium using the link below!

sites.google.com

0

8

40

Rose Yu

@yuqirose

2 years

New paper to appear at #L4DC2022 on Neural Point Process for modeling irregularly sampled event data over space and time. (1/3) #DeepLearning #AI Paper: Code:

2

3

39

Rose Yu

@yuqirose

2 years

Come to our poster today at #NeurIPS2022 and learn about meta-learning and turbulence!

Rose Yu

@yuqirose

2 years

Want to design #DeepLearning models that can generalize across dynamics? Check out our #NeurIPS2022 paper on ``Meta-Learning Dynamics Forecasting''. Paper: Code: (1/3)

8

77

424

1

3

39

Rose Yu

@yuqirose

2 years

Flying to #ICML2022 . Look forward to meeting old and new friends. Ping me if you want to talk about research, life or just good food :)

0

39

Rose Yu

@yuqirose

2 years

#NeurIPS top model from @ucsd_cse Holiday Party. Check out the video from 1:08:35. First time I am in a movie trailer with @BergKirkpatrick @McAuleyLabUCSD #DeepLearning #GPT3

2

1

40

Rose Yu

@yuqirose

3 years

#TimeSeriesWorkshop is back at #ICML2021 ! Extended deadline towards this Friday! Consider submitting!!!

0

5

40

Rose Yu

@yuqirose

5 months

I will be speaking at the upcoming workshop "Learning Collective Variables and Coarse-Grained Models ()" (April 22-26, 2024), hosted by @IMSI_Institute @UChicago . (1/2)

Learning Collective Variables and Coarse Grained Models • IMSI

www.imsi.institute

1

2

39

Rose Yu

@yuqirose

3 years

Today 9 a.m. PDT — 11 a.m. PDT - Poster Session 02 at #ICLR2021 . See you there!

Rose Yu

@yuqirose

3 years

New #ICLR2021 paper on Equivariant Continous Convolution for Trajectory Prediction. We leverage insights from #FluidDnamics to consider the internal symmetry in real-world trajectories. Paper: Code: (1/3)

4

52

262

0

3

39

Rose Yu

@yuqirose

7 months

@baaadas I think the same question was asked 5 years ago. Look at what amazing things these PhDs are doing now! Scientific methods, critical thinking and perseverance, fundamental training in research skills goes a long way!

0

1

38

Rose Yu

@yuqirose

6 years

Our paper with @yaguang_li on 'Diffusion Convolutional RNN' was accepted into #ICLR2018 ! A neural sequence model that learns to forecast on a directed graph.

0

9

37

Rose Yu

@yuqirose

3 years

Easy first shot. One more to go! #thisisourshot

1

0

38

Rose Yu

@yuqirose

2 years

Look forward to speaking at TRIPODS winter school & workshop on #AI and Dynamical Systems with @mraginsky @MFazlyab @eigensteve @ParisPerdikaris !

1

6

37

Rose Yu

@yuqirose

1 year

Flying to @l4dc_conf ! Excited to visit Philadelphia and give a keynote talk! Our PhD students @huiwensun_ @ZihaoKevinZhou will be there presenting their papers too!

L4DC Conference

@l4dc_conf

1 year

Thrilled to announce our 🔥 Keynote Speakers 🔥 for L4DC 2023: @ylecun @yuqirose @robo_kween @vikassindhwani Aaron Ames ( @AMBER_lab ) and Tamer Başar!

0

11

99

0

2

36

Rose Yu

@yuqirose

2 years

Come to our talk at 4:30 pm and poster at 6:30 today at #ICML2022 #DeepLearning -Sequence Model sessions. Learn about how to learn the right amount of #symmetry from turbulence data!

Rose Yu

@yuqirose

2 years

Want to use equivariant networks but the #symmetry in not perfect? We present ``Approximately Equivariant Networks for Imperfectly Symmetric Dynamics", to appear #ICML2022 . Paper: Code: (1/3)

4

7

33

0

4

35

Rose Yu

@yuqirose

2 years

Come to our poster #KDD2022 today, August 16, 4:00 PM-6:00 PM, Room 208AB (Deep Learning: New Architectures and Models) and learn about Multi-Fidelity Uncertainty Quantification! (1/3) Paper: Code:

3

5

35

Rose Yu

@yuqirose

3 years

I had a lot of fun serving as the session chair with @animesh_garg on #DynamicalSystems #Density and #Sparsity . Thanks to @NeurIPSConf for the opportunity!

1

3

34

Rose Yu

@yuqirose

4 years

I stand with the Black community. #BlackLivesMattter

0

2

33

Rose Yu

@yuqirose

3 years

Reviewing #ML #PhD applications is a difficult multi-objective optimization problem. Any advice? - publication? The randomness of #ML reviewing process can obscure the quality of the research. (1/3)

5

0

34

Rose Yu

@yuqirose

2 years

Want to use equivariant networks but the #symmetry in not perfect? We present ``Approximately Equivariant Networks for Imperfectly Symmetric Dynamics", to appear #ICML2022 . Paper: Code: (1/3)

4

7

33

Rose Yu

@yuqirose

1 year

Amazing how much @ucsd_cse has grown!

UCSD CSE

@ucsd_cse

1 year

Happy 35th birthday CSE! That's right - we're celebrating 35 years of Computer Science and Engineering education at @UCSanDiego ! Join us April 14 for a celebration-filled day! @UCSDJacobs More information: #CSECelebrates35 #CSEducation #UCSDCSE

3

7

41

0

2

32

Rose Yu

@yuqirose

4 years

#TimeSeries workshop is back! Now at #KDD2020 Aug 24, 8 - 5 pm PST. Great line of speakers @ProfInderjit @lukaszkaiser @MihaelaVDS , and Nikunj Oza. Web: Zoom: Thanks to @yaguang_li , Sanjay Purushotham for co-organizing!

The 6th SIGKDD Mining and Learning from Time Series Workshop

6th SIGKDD Workshop on Mining and Learning from Time Series (MiLeTS)

kdd-milets.github.io

0

8

32

Rose Yu

@yuqirose

5 years

Excited to give a talk at #kdd2019 about #tensor learning!

Vagelis Papalexakis

@vagelispapalex

5 years

Interested in #tensors for #datascience ? Come by our @kdd_news #kdd2019 workshop on Tensor Methods for Emerging Data Science Challenges at Summit 9- Ground Level, Egan tmr Aug 5, 8am-12pm for an exciting blend of invited talks and posters!

0

6

21

1

2

32