Zeynep Akata @zeynepakata Twitter profile | Pikagi

Pikagi

Zeynep Akata

@zeynepakata

5,655

Followers

274

Following

8

Media

251

Statuses

Professor of Computer Science at @TU_Muenchen and Director @Helmholtz_Munich , @ELLISforEurope Fellow

Munich

https://t.co/aq4SzzK50r

Joined February 2010

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

Pinned Tweet

@zeynepakata

Zeynep Akata

5 months

🌟Exciting news alert! 🌟 I am beyond thrilled to share that in January I am joining @HelmholtzMunich as a director & @TU_Muenchen as a Liesel Beckman distinguished professor! This opportunity marks an incredible leap in my career journey, one I'm deeply grateful for.

Tweet media one

Tweet media two

34

9

539

Last Seen Profiles

@oouou988

@manulysart

@nhikosabs

@mdr_th

@AJB2295

@tayranga

@penguin_033612

@ShipsLucia

@LukeLRPS

@Nos_North

@amedeegagabriel

@BLWalkOn

@unknown47128686

@2Iii97gUkKkSac1

@Bagsssssnf70508

@nanamirona

@DookFnNookem

@GatorsLaxClub

@amayajsanchez

@joshua_meyers

@bramkeijsers

@WilliamAronste3

@KatarzynaStarz5

@gripeyhypeman_

@foxfeather

@jaaiwtss

@UlisesMoss59146

@rinka3571431525

@Orthotropics

@Mustafacevik10

@GasparValverde

@SrtaMimiiGoblin

@lennyx71

@sissy_secrets

@GopherMBB

@Exo54796

@zeynepakata

Zeynep Akata

3 years

It is an honor to receive this award today. Thanks to the German Pattern Recognition Society for their support. It is great to be in Tübingen and be a part of @ml4science , @uni_tue , @MPI_IS

@ml4science

ML for Science

3 years

Fantastic news: Our Cluster Professor @zeynepakata has just been granted the “German Pattern Recognition Award”! 🍾🍾🍾The prize aims to promote outstanding young scientists in the fields of pattern recognition, computer vision and machine learning. Congrats, @zeynepakata ! 1/1

Tweet media one

5

14

102

33

18

395

@zeynepakata

Zeynep Akata

2 years

It’s an honor to receive the ECVA Young Researcher Award 2021 🎉 Special thanks to my former PhD advisor @CordeliaSchmid for the nomination & the executive board of ECVA for the recognition

@sitzikbs

Yizhak Ben-Shabat (Itzik) 💔

2 years

ECVA young researcher awards: congrats @zeynepakata

Tweet media one

1

1

12

21

13

333

@zeynepakata

Zeynep Akata

2 years

6 papers are accepted to #CVPR2022 🎉 congratulations to my students and postdocs! More details will follow @ExplainableML . Supported by @uni_tue @ml4science @MPI_IS @ELLISforEurope

5

9

278

@zeynepakata

Zeynep Akata

4 years

ELLIS offers an interdisciplinary PhD program where every PhD student is supervised by one ELLIS fellow/scholar and one ELLIS member from a different country and conducts a 1 year exchange at the other location. Application deadline: 1.12.2020

2

70

251

@zeynepakata

Zeynep Akata

2 years

We are looking for PhD candidates (deadline November 1st) and looking forward to your applications!

@ExplainableML

Explainable Machine Learning

2 years

If you are interested in joining our Explainable Machine Learning Group () and to work on topics ranging from XAI, OOD Generalization and Multimodal Learning to Zero-Shot Learning, consider applying through the great IMPRS-IS graduate program!

0

14

62

11

63

245

@zeynepakata

Zeynep Akata

11 months

It is a great honour to receive this award. I'd like to thank Alfried Krupp von Bohlen und Halbach-Foundation for their generosity, @uni_tue for the nomination, @ml4science @MPI_IS @MPICybernetics @Cyber_Valley for the excellent research environment they create for us.

@ml4science

ML for Science

11 months

Our cluster professor @zeynepakata receives the Alfried Krupp Prize 2023! Congratulations! More about Akata's research here: @ExplainableML @uni_tue @uni_tue_exstra #Prize

Tweet media one

4

13

84

12

5

189

@zeynepakata

Zeynep Akata

3 months

🚀 Exciting Opportunity Alert! 🚀 🔍 Join us as a Postdoctoral Researcher (fully funded) at the Helmholtz Munich Institute for Explainable Machine Learning and TUM Chair of Interpretable and Reliable Machine Learning! @TU_Muenchen @Helmholtz_Munich @ELLISforEurope

3

31

159

@zeynepakata

Zeynep Akata

2 years

4 papers are accepted to #ECCV2022 🎉 The topics range from explainable sketch abstraction, uncertainty, audio-visual zero-shot learning, deep metric learning. More details will follow @ExplainableML . Supported by @uni_tue @ml4science @MPI_IS @ELLISforEurope

2

7

153

@zeynepakata

Zeynep Akata

4 years

We are looking for a postdoc to join our new Explainable Machine Learning lab within the Cluster of Excellence @uni_tue starting as soon as possible #MachineLearning #NLProc #ComputerVision

4

65

149

@zeynepakata

Zeynep Akata

2 years

If you‘d like to have academic independence and collaborate with us in Tübingen immediately after your PhD, this is not to miss! We sincerely hope that strong female candidates will apply as well.

@ml4science

ML for Science

2 years

Just been awarded your PhD? We have several open positions as Early Career Group Leaders! For scientists researching core machine learning (ML) or applying ML to a scientific discipline of your choice. We encourage women&underrepresented groups to apply:

Tweet media one

1

67

149

2

33

147

@zeynepakata

Zeynep Akata

2 years

I am looking forward to collaborating with such a team diverse in every dimension! If you are looking for a PhD in the intersection of #ML & #cognitivescience please apply! @MPICybernetics @DeepMind @uni_tue @ml4science

@cpilab

Computational Principles of Intelligence Lab

2 years

We are looking to hire a fully-funded PhD-student to work on Cognitive Models of Meta-Reinforcement Learning. The student would be co-supervised by Eric and @janexwang , as well as collaborate with @zeynepakata and Matt Botvinick: Deadline: Dec 21st

1

40

122

1

30

147

@zeynepakata

Zeynep Akata

5 years

We are looking for PhD students for projects related to Explainable Machine Learning, the application deadline is November 6th!

2

90

140

@zeynepakata

Zeynep Akata

2 years

We are looking for a Research Fellow (E14 TV-L, 100%) in @ExplainableML team @ml4science and @uni_tue in collaboration with @trevordarrell from @UCBerkeley . Deadline: 15 February. Come and join us for this exceptional opportunity!

0

43

122

@zeynepakata

Zeynep Akata

3 years

Looking forward to giving a talk at the TUM AI lecture series tomorrow.

@MattNiessner

Matthias Niessner

3 years

Tomorrow in our TUM AI - Lecture, we have @zeynepakata talking about Explainability and Compositionality for Visual Recognition! Live Stream here: Starts tomorrow at 6pm CEST / 9am PST!

Tweet media one

3

15

133

0

7

115

@zeynepakata

Zeynep Akata

3 years

Full Professor (W3) opening in #ComputerScience at the University of Tübingen @uni_tue , in the same campus as @ml4science , @MPI_IS , @MPICybernetics , @MPI_for_DB , @Cyber_Valley . Deadline for applications: March 12th!

1

42

103

@zeynepakata

Zeynep Akata

3 years

We are accepting PhD applications! Deadline November 2nd.

@ExplainableML

Explainable Machine Learning

3 years

If you are interested in doing a PhD with us, consider applying through the IMPRS-IS program. Deadline: November 1st.

0

18

38

2

18

92

@zeynepakata

Zeynep Akata

4 years

Checkout our #NeurIPS2020 paper 'Attribute Prototype Network for Zero-Shot Learning': a network that can visually explain its behavior by learning attribute prototypes that are then used to predict and localise class-discriminative attributes for an image.

1

9

92

@zeynepakata

Zeynep Akata

2 years

We are presenting six papers in the main conference of #CVPR2022 next week. Come and join us in New Orleans!

@ExplainableML

Explainable Machine Learning

2 years

If you are at #CVPR2022 , come check out one of our six publications! We have topics ranging from training on partially labelled dataset to (multi-modal) contrastive metric learning and all manners of zero-shot learning! A quick 🧵 (sorted by date):

1

8

50

2

5

90

@zeynepakata

Zeynep Akata

2 years

Happy international women’s day! I am incredibly grateful to all the strong women who I had the pleasure of meeting and working together throughout my journey.

0

2

87

@zeynepakata

Zeynep Akata

3 years

We have an open PhD position (fully funded, E13 TV-L, 80%) in compositional data synthesis with @anna_khoreva in @Cyber_Valley @uni_tue (Application deadline: 31 May) For more information:

1

32

85

@zeynepakata

Zeynep Akata

4 years

We are looking for independent research group leaders for Machine Learning combined with #NLP , #linguistics and other disciplines in Cluster of Excellence #MachineLearning at the University of Tübingen @uni_tue (deadline for application is April 30).

0

40

74

@zeynepakata

Zeynep Akata

8 months

Very excited about coming to #ICCV2023 and presenting 4 papers from our @ExplainableML group (👇is one) at the main conference in person! My first since 2019 😄

@confusezius

Karsten Roth

8 months

CLIP + LLMs: A modern success story 🌟. LLM provides detailed class context, feeds it back into CLIP - and you have yourself an improved open-vocabulary classifier 💫. 🤔Turns out the same gain can often be achieved with random words and characters instead. #ICCV2023

Tweet media one

Tweet media two

7

34

197

0

4

72

@zeynepakata

Zeynep Akata

4 years

We are looking for a PhD student (fully funded) within the IMPRS program. The deadline for applications is November 2nd:

0

17

70

@zeynepakata

Zeynep Akata

4 years

Looking forward to the #WiCV workshop at #ECCV2020 !

@WiCVworkshop

WiCV

4 years

We are pleased to welcome @dimadamen , @FidlerSanja and @zeynepakata as our guest speakers at #WiCV . They will be joined by Rahul Sukthankar for a panel discussing diversity in computer vision. Leave your anonymous questions for the panel here:

Tweet media one

0

17

86

0

1

66

@zeynepakata

Zeynep Akata

3 months

More information (paper, code, blogpost) on our #ICLR2024 spotlight paper "Fantastic Gains and Where to Find Them - On the Existence and Prospect of General Knowledge Transfer":

@confusezius

Karsten Roth

3 months

🤔 Weight averaging is great, but can you merge arbitrary trained models? Our #ICLR2024 spotlight shows that you can - and should! For example, we find that weak models have unique knowledge missed by bigger and better ones, and careful integration can make them even stronger!

Tweet media one

Tweet media two

3

53

320

0

4

59

@zeynepakata

Zeynep Akata

2 years

I am looking forward to giving a keynote at @UncertaintyInAI at 9am CEST today. I will talk about explainability via conversations and my thoughts on uncertainty.

0

3

57

@zeynepakata

Zeynep Akata

5 years

Deeply honoured to be awarded an ERC-2019 Starting Grant! The grant (DEXIM) comes with a funding of 1.5M EUR to pursue cutting edge research on ML, language and vision, aiming to explain the decisions of machine learning models to the user.

Tweet card media

Open to the world: 51 nationalities among winners of 2019 ERC Starting Grants

6

2

57

@zeynepakata

Zeynep Akata

4 years

Excited to share our work on “Modeling Conceptual Understanding in Image Reference Games”, appearing as a spotlight in #NeurIPS 2019 Paper: Code: with @_rodolfocorona_ and Stephan Alaniz

Tweet card media

GitHub - rcorona/conceptual_img_ref: Implementation for: https://arxiv.org/abs/1910.04872

Implementation for: https://arxiv.org/abs/1910.04872 - rcorona/conceptual_img_ref

2

10

54

@zeynepakata

Zeynep Akata

1 year

It was a pleasure to speak at the #ML4Earth #XAI workshop in Munich today @xiaoxiang_zhu and her group are doing super exciting work at @TU_Muenchen and @helmholtz_ai

@xiaoxiang_zhu

Xiaoxiang ZHU

1 year

Ongoing - super exciting keynote from Prof Zeynep Akata @zeynepakata @uni_tue on #xAI for #Vision #NLP and #EarthObservation at our #ML4Earth xAI workshop organized by @TU_Muenchen @Zhu_XLab @ai4eo_de @helmholtz_ai

Tweet media one

0

3

18

0

3

49

@zeynepakata

Zeynep Akata

3 years

Can we recognize state-object compositions within ~30k classes? Yes! Check out our @CVPR '21 paper: Open World Compositional Zero-Shot Learning. Joint work with @massi_manc , @ferjadnaeem , @xyongqin Paper: Code:

Tweet card media

GitHub - ExplainableML/czsl: PyTorch CZSL framework containing GQA, the open-world setting, and the...

PyTorch CZSL framework containing GQA, the open-world setting, and the CGE and CompCos methods. - ExplainableML/czsl

1

9

49

@zeynepakata

Zeynep Akata

3 years

Check out our #CVPR21 paper ‘Distilling Audio-Visual Knowledge by Compositional Contrastive Learning’ joint work with @yanbei_c @xyongqin , A.Sophia Koepke, Ying Shan Paper: Code:

Tweet card media

GitHub - ExplainableML/CCL: Code on Paper [CVPR2021]Distilling Audio-Visual Knowledge by Composit...

Code on Paper [CVPR2021]Distilling Audio-Visual Knowledge by Compositional Contrastive Learning - ExplainableML/CCL

1

12

49

@zeynepakata

Zeynep Akata

4 years

Looking forward to the #RIIAA2020 summer school and conference on August 25-28!

@riiaa_org

RIIAA

4 years

#RIIAA2020 is close and we are very happy to continue announcing more amazing speakers participating this year. Now is the turn of @zeynepakata from the University of Tübingen, panelist of Computer Vision #AI

Tweet media one

0

3

15

1

5

46

@zeynepakata

Zeynep Akata

3 years

Checkout 'ImageNet: past, present and future' workshop at #NeurIPS2021 for a great lineup of speakers and consider submitting your contributions (Deadline: September 18th)! @coallaoh @dlarlus @giffmana @SanghyukChun @XiaohuaZhai

@giffmana

Lucas Beyer (bl16)

3 years

Our NeurIPS'21 workshop on "ImageNet: past, present, and future" has been accepted! I'm excited about our speaker line-up. I'm even more excited to see what papers researchers will submit to the workshop! Please spread the word, and consider submitting.

Tweet media one

2

44

255

0

10

45

@zeynepakata

Zeynep Akata

3 years

Check out our @CVPR '21 paper: Our RDTC model combines classical #MachineLearning with #DeepLearning to improve model explanation. Joint work with Stephan Alaniz, Diego Marcos, Bernt Schiele Paper: Code:

Tweet card media

GitHub - ExplainableML/rdtc: PyTorch implementation of Learning Decision Trees Recurrently Through...

PyTorch implementation of Learning Decision Trees Recurrently Through Communication (RDTC) - ExplainableML/rdtc

1

7

42

@zeynepakata

Zeynep Akata

3 years

Check out our #CVPR21 paper ‘Learning Graph Embeddings for Compositional Zero-shot Learning’ joint work with @ferjadnaeem @xyongqin and @fedassa Paper: Code:

Tweet card media

GitHub - ExplainableML/czsl: PyTorch CZSL framework containing GQA, the open-world setting, and the...

PyTorch CZSL framework containing GQA, the open-world setting, and the CGE and CompCos methods. - ExplainableML/czsl

2

5

41

@zeynepakata

Zeynep Akata

4 years

Congratulations to Anna Sepliarskaia for successfully defending her PhD thesis @UvA_Amsterdam . It is great to wear one of these robes (and the neck tie that traditionally goes with it)😄with Sonja Smets and @hanedhinda .

Tweet media one

0

0

39

@zeynepakata

Zeynep Akata

1 year

Happy international women‘s day! 🎉

@TueNeuroCampus

TübingenNeuroCampus

@TueNeuroCampus

1 year

📢For International Women's Day #IWD2023 a shout out to the amazing, creative and inspiring female #neuroscientists working in Tübingen 🎉🎉 @uni_tue @uktuebingen @MPICybernetics @ml4science #InternationalWomensDay #InternationalWomensDay2023 #InternationalerFrauentag

Tweet media one

0

4

31

0

0

38

@zeynepakata

Zeynep Akata

3 years

Come and visit us in Session 1 #ICCV2021 on Tuesday 12.10 at 10am EDT (4pm CEST) and on Thursday 14.10 at 5pm EDT (11pm CEST) @ExplainableML @uni_tue @ml4science @UniofOxford @MPI_IS

@maximek3

Maxime Kayser

3 years

🆕 Paper at #ICCV2021 💥 😈e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks (VL-NLE) with @oanacamb , L. Salewski, @CorEmde , @zeynepakata , and T. Lukasiewicz @UniofOxford @uni_tue #ML #CV #XAI #NLProc (1/6)

2

20

56

0

4

38

@zeynepakata

Zeynep Akata

4 years

#DAAD offers a postdoctoral networking tour in #ML / #AI Come and visit us in @uni_tue @Cyber_Valley (Deadline: 16 August)

Details and Application

Exploring research and career options and connect with the German artificial intelligence community.

0

14

36

@zeynepakata

Zeynep Akata

1 year

New pre-print: In-Context Impersonation Reveals Large Language Models' Strengths and Biases. Lead by @L_Salewski and in collaboration with Stephan Alaniz, Isabel Rio-Torto, @cpilab . 1/4

Tweet media one

1

7

37

@zeynepakata

Zeynep Akata

2 months

Waseda Symphony Orchestra Tokyo gave a mind blowing concert in Munich just now at Isarphilarmonie. A wonderful way to advertise a university! 😊

0

1

37

@zeynepakata

Zeynep Akata

1 year

I am looking forward to giving a keynote at the #HelmholtzAICon 2023 in Hamburg!

@helmholtz_ai

Helmholtz AI

1 year

Get ready for an unforgettable conference experience! #HelmholtzAICon 2023 🎙️ We're thrilled to announce our Keynote speaker lineup, and joining us on Day 1 is @zeynepakata , Professor of Computer Science at the University of Tübingen. 📢 Save the date: 12 June in Hamburg!

Tweet media one

0

2

12

0

0

36

@zeynepakata

Zeynep Akata

2 years

10 days left to apply!

@zeynepakata

Zeynep Akata

2 years

We are looking for a Research Fellow (E14 TV-L, 100%) in @ExplainableML team @ml4science and @uni_tue in collaboration with @trevordarrell from @UCBerkeley . Deadline: 15 February. Come and join us for this exceptional opportunity!

0

43

122

0

14

36

@zeynepakata

Zeynep Akata

1 year

After 3 extremely productive years with us, our @massi_manc has decided to move on to build his own group @UniTrento . Please consider applying to work with him, we have absolutely loved it, I am sure you would too!

@massi_manc

Massimiliano Mancini

1 year

After ~3 years at @ExplainableML in @uni_tue , I joined the Multimedia and Human Understanding Group (MHUG) at @UniTrento_DISI as an assistant professor (RTD-a)!

Tweet media one

16

5

143

0

1

35

@zeynepakata

Zeynep Akata

3 years

If you’d like to do a PhD with us and collaborate with another research lab in Europe, apply to @ELLISforEurope PhD program. We are accepting applications until November 15th!

@ExplainableML

Explainable Machine Learning

3 years

If you are interested in doing a PhD with us, consider applying through the ELLIS PhD program. Deadline: November 15th.

0

6

8

2

9

31

@zeynepakata

Zeynep Akata

2 years

It was great to meet @SergeBelongie today at the IMPRS-IS evaluation event and present to a large audience after such a long break!

@SergeBelongie

Serge Belongie

2 years

Prof. @ZeynepAkata presents her group’s work on zero-shot learning w/external knowledge @uni_tue @MPI_IS

Tweet media one

Tweet media two

1

4

74

1

2

31

@zeynepakata

Zeynep Akata

4 years

The German Conference on Pattern Recognition will take place from September 28 to October 1 in Tübingen @uni_tue (will be a virtual conference if necessary). Paper submission deadline is July 10, 2020.

0

9

31

@zeynepakata

Zeynep Akata

10 months

A big congratulations to our Karsten Roth @confusezius for winning a QIF Europe award 🎉

@QCOMResearch

Qualcomm Research & Technologies

10 months

QIF Europe is an excellence award through which @Qualcomm rewards and mentors the most innovative PhD students in Europe working on breakthrough #AI and #cybersecurity solutions. Congratulations @tychovdo @confusezius @SiweiZhang13 and Attri Bhattacharyya

Tweet media one

0

7

26

1

0

30

@zeynepakata

Zeynep Akata

2 months

The deadline is this Friday. Looking forward to your applications!

@zeynepakata

Zeynep Akata

3 months

🚀 Exciting Opportunity Alert! 🚀 🔍 Join us as a Postdoctoral Researcher (fully funded) at the Helmholtz Munich Institute for Explainable Machine Learning and TUM Chair of Interpretable and Reliable Machine Learning! @TU_Muenchen @Helmholtz_Munich @ELLISforEurope

3

31

159

0

3

29

@zeynepakata

Zeynep Akata

2 years

We are also looking for PhD students through the #ELLISPhD program (joint PhD in two institutions from two different European countries). Deadline November 15. Application link:

Tweet card media

ELLIS PhD Program: Call for applications 2022

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of...

@ExplainableML

Explainable Machine Learning

2 years

Come work with us as part of the #ELLISPhD family if you are interested in research ranging from explainable and interpretable ML, multimodal and zero-shot learning to contrastive and out-of-distribution capable representation learning!

1

1

8

3

5

29

@zeynepakata

Zeynep Akata

4 years

The talks from last weeks #ml4science2020 conference are on youtube now! 👇

@ml4science

ML for Science

4 years

Did you miss a talk at our conference #ml4science2020 last week? Don't worry, the videos of all talks are now availabe on Youtube:

1

14

38

0

2

26

@zeynepakata

Zeynep Akata

2 years

Come and join us on Tuesday Dec 7th at 8:30AM-10AM PST #NeurIPS2021

@ExplainableML

Explainable Machine Learning

2 years

With #NeurIPS '21 right around the corner, make sure to check out "Robustness via Uncertainty-aware Cycle Consistency" w/ @uddupa , @yanbei_c & @zeynepakata ! @uni_tue @MPI_IS and come visit us next week! 1/3

1

9

34

0

4

27

@zeynepakata

Zeynep Akata

1 year

Compositionality capabilities of image generation with diffusion models have been extensively discussed & several model improvements have been proposed. In an orthogonal way, we show that diffusion models are actually compositional if you dig them deep.

@ShyamgopalKart1

Shyamgopal Karthik

@ShyamgopalKart1

1 year

We are much better at evaluating text-to-image alignment these days e.g. breaking up the process into a series of question-answers, or directly measure it using a model trained on human preferences. Can we use this to improve the generated images? 👉

1

8

44

0

3

26

@zeynepakata

Zeynep Akata

2 years

I am looking forward to speaking at the #GrowingUpInScience event next Tuesday ☺️

@mindfulsci_tue

Mindful Science

@mindfulsci_tue

2 years

Join our next #GrowingUpInScience 🥼🧠 on May 24th 6-7pm 📆 with @zeynepakata to learn about her story, struggles, and doubts on her journey to become a professor of #ComputerScience 🖥 Register with the link the bio!

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

5

8

1

4

26

@zeynepakata

Zeynep Akata

3 years

Happening today in the first session of #CVPR2021 (11am EDT, 5pm CET) paper ID: 1098. Come and check it out!

@zeynepakata

Zeynep Akata

3 years

Check out our #CVPR21 paper ‘Learning Graph Embeddings for Compositional Zero-shot Learning’ joint work with @ferjadnaeem @xyongqin and @fedassa Paper: Code:

2

5

41

0

3

26

@zeynepakata

Zeynep Akata

2 years

We are presenting the four papers below in the main conference of #ECCV2022 !

@ExplainableML

Explainable Machine Learning

2 years

👋At #ECCV2022 and looking for posters to visit? Interested in an @ELLISforEurope or #IMPRSIS PhD with us? Talk to us at the poster sessions, with topics from audio-visual zero-shot learning, sketch abstraction, uncertainty quantification to probabilistic contrastive learning:

1

4

35

0

2

26

@zeynepakata

Zeynep Akata

5 months

At Helmholtz, leading the Institute for Explainable Machine Learning, and at TUM, chairing the Interpretable and Reliable Machine Learning group, I'm eager to move forward explainable ML and multimodal learning.

1

1

25

@zeynepakata

Zeynep Akata

2 years

Interesting read to find out how GPT-3 compares with humans wrt several well established criteria from cognitive psychology.

@cpilab

Computational Principles of Intelligence Lab

2 years

Many things have been said about large language models (including GPT-3). In new work with @atze_dota , we used tools from cognitive psychology to study how GPT-3 makes decisions, searches for information, deliberates, and reasons causally, and compared its behavior to humans.

Tweet media one

11

98

343

1

5

23

@zeynepakata

Zeynep Akata

6 days

Our group is presenting three papers at #ICLR2024 . Unfortunately I couldn’t go this year but @confusezius , @LucaEyring and @lukas_thede are there. Please go and talk to them, they’ll be happy to see you!

@ExplainableML

Explainable Machine Learning

6 days

Join us at #ICLR2024 on Wednesday and Friday for 🗓️May 8th 4:30pm, S4: Training-free text-conditional image retrieval, 🗓️May 8th 4:30pm, S4: Unbalanced optimal transport for unpaired translation tasks, 🗓️May 10th 4:30pm, S8 - Spotlight: General model merging and transfer!

0

0

6

0

4

25

@zeynepakata

Zeynep Akata

3 years

Happening today in the fourth session of #CVPR2021 (11am EDT, 5pm CET) paper ID: 7256. Come and check it out!

@zeynepakata

Zeynep Akata

3 years

Can we recognize state-object compositions within ~30k classes? Yes! Check out our @CVPR '21 paper: Open World Compositional Zero-Shot Learning. Joint work with @massi_manc , @ferjadnaeem , @xyongqin Paper: Code:

1

9

49

0

2

23

@zeynepakata

Zeynep Akata

1 year

Proud to be a part of this work! LLMs have gotten so well at standard conversational tasks, now it is time to evaluate how easy it is to effect their psychology and make them biased 😲

@cpilab

Computational Principles of Intelligence Lab

1 year

New pre-print: Using computational psychiatry to understand LLMs, we find that GPT-3.5 responds to anxiety-inducing prompts with increased exploration and biases. Joint work with @juliancodaforno @WitteKristin @akjagadish Marcel Binz and @zeynepakata .

1

30

100

0

0

22

@zeynepakata

Zeynep Akata

1 year

Congratulations @cpilab 🎉 it was a pleasure to work with you, I have learned a lot! Hopefully more will come 😊

@cpilab

Computational Principles of Intelligence Lab

1 year

It's a huge honor to have our work on understanding large language models using tools from psychology and psychiatry featured in this week's @derspiegel . This was a big team effort working together with @juliancodaforno @WitteKristin @akjagadish , Marcel Binz, and @zeynepakata .

Tweet media one

Tweet media two

Tweet media three

Tweet media four

2

7

45

1

1

21

@zeynepakata

Zeynep Akata

3 years

Join us in #ICCV2021 Session 7 at 8am EDT (2pm CEST) today and 3pm EDT (9pm CEST) on Friday if you are interested in Explainable #ML @uni_tue @ml4science @MPI_IS and at Naver AI Lab

@coallaoh

Seong Joon Oh

3 years

Introducing a new paper with Jae Myung Kim, @junsukchoe , @zeynepakata @ ICCV 2021: Keep CALM and improve your visual feature attribution. Paper: Code: Keep reading if you have used CAM before - worth your time! [1/13]

4

19

63

0

2

19

@zeynepakata

Zeynep Akata

8 months

Congratulations @L_Salewski , Isabel, Stephan and @cpilab 🎉 this was a real turnaround! More details will follow shortly, stay tuned…

@L_Salewski

Leonard Salewski

8 months

Thrilled to share that my research on In-Context Impersonation in Large Language Models has been accepted as a spotlight paper at #NeurIPS2023 🎉🚀! Joint work with Stephan Alaniz, Isabel Rio-Torto, @cpilab and @zeynepakata . Check out the paper here:

0

1

24

0

1

19

@zeynepakata

Zeynep Akata

2 years

Fine-Grained Zero-Shot Learning with DNA as Side Information at #NeurIPS2021 Thursday Dec 9th at poster session 4 with @badirli_ George Mohler, @SciencePicard and @mm_dundar Paper:

@badirli_

Sarkhan Badirli

2 years

Come and visit us today between 7:30-9:00pm EST at #NeurIPS Poster session 4, Spot D1. #NeurIPS virtual world is DOPE

Tweet media one

0

0

5

0

3

19

@zeynepakata

Zeynep Akata

1 year

I am looking forward to speaking at the @CambridgeEllis seminar series on 30th November afternoon!

@CambridgeEllis

CambridgeEllisUnit

@CambridgeEllis

1 year

We are looking forward to our next Seminar Speaker @zeynepakata from @uni_tue who will speaking about "Explainability in Deep Learning Through Communication", join us here: #machinelearning #ai

Tweet media one

0

9

31

0

1

18

@zeynepakata

Zeynep Akata

8 months

Proud of you, Eric! Can’t find too many more words to say… I have seen from the first hand how much work went into this. Very well deserved! 🤗🥰

@cpilab

Computational Principles of Intelligence Lab

8 months

Extremely happy that our #ERCStG proposal #TACOS got funded! Over the next 5 years, we will use tools from cognitive science to better understand large language models. This really took a village. Thanks to my lab, colleagues, and family for all of their support. @ERC_research

14

10

91

0

0

18

@zeynepakata

Zeynep Akata

2 months

I am looking forward to speaking at the #HelmholtzImaging Conference on 14-15 May!

@HelmholtzMunich

Helmholtz Munich | @HelmholtzMunich

@HelmholtzMunich

2 months

❗Join the 4th #HelmholtzImaging Conference 📅 14-15 May 2024 📢Register & submit your abstract by 𝟮𝟳 𝗠𝗮𝗿𝗰𝗵 𝟮𝟬𝟮𝟰 #HIConference2024 Highlights: Keynotes by #HelmholtzMunich expert @zeynepakata ( @TU_Muenchen ) & Joost Batenburg (Leiden Uni)

Tweet media one

0

1

6

0

2

17

@zeynepakata

Zeynep Akata

5 months

I am grateful for this chance to advance our research and shape the future of @ExplainableML . Let's embrace this journey together! 🚀✨We're on the lookout for exceptional talent to join our research groups—stay tuned for opportunities!

Tweet media one

0

1

17

@zeynepakata

Zeynep Akata

3 years

This 👇

@cpilab

Computational Principles of Intelligence Lab

3 years

In a new paper just out in @iScience_CP and together with Peter Dayan, we propose to turn the lens of computational psychiatry onto computers to illuminate their systematic failures.

Tweet media one

3

44

171

0

0

14

@zeynepakata

Zeynep Akata

5 months

Heartfelt thanks to the @uni_tue , especially the @ml4science and TUE AI Center, for their invaluable support in shaping my path & to my phenomenal team: I'm immensely grateful for your contributions—here's the exciting part: almost all of us are moving to Munich together!

Tweet media one

Tweet media two

1

1

14

@zeynepakata

Zeynep Akata

2 months

Fresh blogpost from Luca on our ICLR24 paper in the topic of unpaired translation using optimal transport. We show results not only on i2i but also single cell translation tasks. Please have a look!

@LucaEyring

Luca Eyring @ICLR

2 months

Dealing with undesired distribution shifts in unpaired translation tasks? Our #ICLR2024 paper shows how to mitigate them leveraging Unbalanced OT! We propose a method to incorporate unbalancedness into any neural Monge map estimator and demonstrate the benefits of unbalancedness.

Tweet media one

2

19

90

0

1

13

@zeynepakata

Zeynep Akata

3 months

📅 Starting Date: June 1st, 2024 (negotiable) 💼 Position: Postdoc (E13 or E14 TVöD, 100%) 🌐 Location: Munich, Germany 🔎 About the Position: ✅ PhD in CS, ML, CV, NLP, or related fields ✅ Strong publication record in top-tier conferences ✅ Experience in supervision

1

1

11

@zeynepakata

Zeynep Akata

3 years

Happening today/tomorrow in the fifth session of #CVPR2021 (22pm EDT, 4am CET) paper ID: 3368. Come and check it out!

@zeynepakata

Zeynep Akata

3 years

Check out our #CVPR21 paper ‘Distilling Audio-Visual Knowledge by Compositional Contrastive Learning’ joint work with @yanbei_c @xyongqin , A.Sophia Koepke, Ying Shan Paper: Code:

1

12

49

0

2

11

@zeynepakata

Zeynep Akata

10 months

Thank you @SabrinaPatsch for her interesting questions, guidance and translation in this interview. It was a great pleasure talking to her!

@SabrinaPatsch

Sabrina Patsch

10 months

#KuenstlicheIntelligenz ist undurchsichtig: Meist ist unklar, wie ein Ergebnis zustande kam und ob es vertrauenswürdig ist. @zeynepakata von @ml4science @uni_tue will das ändern – mit erklärbarem #MachineLearning . @Tagesspiegel (T+)

0

1

10

0

0

10

@zeynepakata

Zeynep Akata

4 years

@MPI_IS has recently announced 3 independent #MaxPlanck research group leader positions. Come and be a part of the rapidly growing #ML research ecosystem in Tübingen! Deadline: July 22nd.

@MPI_IS

Intelligent Systems

4 years

Our Institute and the #CyberValley initiative are looking for outstanding candidates in the field of intelligent systems to establish three new independent #MaxPlanck #Research Groups. Apply or spread the word!

Tweet media one

0

29

65

0

4

10

@zeynepakata

Zeynep Akata

3 months

📝 How to Apply: Send your application to zeynep.akata @tum .de with subject line [EML open topic postdoc application] by March 15th, 2024. Don't hesitate to reach out with any questions! 💡 More info: #JobOpening #AcademicTwitter #MLResearch

0

1

10

@zeynepakata

Zeynep Akata

3 years

Happening today in the tenth session of #CVPR2021 (11am EDT, 5pm CET) paper ID: 5223. Come and check it out!

@zeynepakata

Zeynep Akata

3 years

Check out our @CVPR '21 paper: Our RDTC model combines classical #MachineLearning with #DeepLearning to improve model explanation. Joint work with Stephan Alaniz, Diego Marcos, Bernt Schiele Paper: Code:

1

7

42

0

1

10

@zeynepakata

Zeynep Akata

2 years

@lawrennd @PhilippHennig5 @KyleCranmer @CellTypist @jakhmack I am currently on a leave and will therefore not reply to twitter threads :)

1

0

10

@zeynepakata

Zeynep Akata

2 years

Happening now!

@ExplainableML

Explainable Machine Learning

2 years

With #NeurIPS '21 right around the corner, make sure to check out "Robustness via Uncertainty-aware Cycle Consistency" w/ @uddupa , @yanbei_c & @zeynepakata ! @uni_tue @MPI_IS and come visit us next week! 1/3

1

9

34

0

0

10

@zeynepakata

Zeynep Akata

4 years

Our attribute prototypes can transfer knowledge from seen to unseen classes boosting the performance of zero-shot learning via locality enhanced image representations that can visualise class discriminative attributes accurately.

Tweet card media

Attribute Prototype Network for Zero-Shot Learning

From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes,...

1

1

10

@zeynepakata

Zeynep Akata

6 days

If you are interested in image retrieval with compositional captions without training or tuning the model, please talk to @confusezius at #ICLR2024 after his presentation today. Details below!

@ExplainableML

Explainable Machine Learning

6 days

Today (May 8th, 4:30pm at Session 4) @confusezius will present our work on image retrieval under arbitrary text conditions - without explicit training data and model tuning required! Great work by @ShyamgopalKart1 @confusezius @massi_manc @zeynepakata !

0

1

5

0

1

13

@zeynepakata

Zeynep Akata

4 years

Twitter has become a better place then!

@UlrikeLuxburg

Ulrike Luxburg

4 years

Finally started a twitter account ... @CellTypist @PhilippHennig5 @jakhmack @zeynepakata @MatthiasBethge

11

2

67

0

0

8

@zeynepakata

Zeynep Akata

3 months

🔬 Possible Research Topics: ✨ Multimodal Learning ✨ Explainable ML ✨ Large Foundational Models ✨ Scene & Video Understanding ✨ Low-shot Learning & more! 👩‍💻👨‍💻 Join us in shaping the future of Explainable Machine Learning!

1

0

7

@zeynepakata

Zeynep Akata

3 years

@confusezius @ELLISforEurope @OriolVinyalsML @uni_tue Looking forward to it!

1

0

7

@zeynepakata

Zeynep Akata

6 days

@CompHealthMuc @HelmholtzMunich @Pseudomanifold @vincefort @k__niki @fabian_theis Also @cpilab

0

0

1

@zeynepakata

Zeynep Akata

3 years

We solve the classification task in a two-agent framework. The recurrent decision-tree agent asks binary questions and the attribute-based agent provides the yes/no answer w.r.t. the image.

1

0

6

@zeynepakata

Zeynep Akata

2 years

Application link:

0

0

6

@zeynepakata

Zeynep Akata

4 years

@TheCharleyWu @uni_tue @ml4science Looking forward to collaborating with you, Charley! Welcome to the @uni_tue family!

0

0

5

@zeynepakata

Zeynep Akata

4 years

@tkasarla_ @2ayasalama This is an exchange program. Your PhD advisor and the supervisor from the host institution need to be ELLIS members. You can find the list of members here: @ELLISforEurope

1

0

5

@zeynepakata

Zeynep Akata

4 years

Joint work with: @wenjia43411575 @xyongqin @WangJiuniu and Bernt Schiele.

0

0

5

@zeynepakata

Zeynep Akata

1 year

We evaluate the usefulness of descriptions generated by in-context impersonation for vision and language tasks by using them for CLIP zero-shot classification. On CUB and Stanford Cars we see increasing performance with age and expertise and reveal biases wrt race and gender. 3/4

Tweet media one

1

0

4

@zeynepakata

Zeynep Akata

1 year

We use pre-trained instruction-following LLMs like #Vicuna13B and #ChatGPT and instruct them to impersonate a persona with the phrase "If you were a {persona}", an approach that we call "in-context impersonation". We study different ages, expertise, races and genders. 2/4

Tweet media one

1

0

4

@zeynepakata

Zeynep Akata

4 years

@KyleCranmer @ml4science I would love to discuss further about it!

0

0

4

@zeynepakata

Zeynep Akata

3 years

@Michael_J_Black @CSProfKGD Thank you for sharing this wonderful story and the pictures 😊

0

0

4

@zeynepakata

Zeynep Akata

4 years

@kenedylounge Trakya -> Bonn/Aachen -> Grenoble -> Saarbrücken -> Amsterdam -> Tübingen

2

0

4

@zeynepakata

Zeynep Akata

2 years

@Michael_J_Black @Cyber_Valley CVPR 2022 😄

0

0

4

@zeynepakata

Zeynep Akata

3 years

RDTC can also provide fine-grained explanations by using human-understandable attributes as binary splits while at the same time being more scalable and flexible than other neural decision trees.

0

0

4

@zeynepakata

Zeynep Akata

4 years

@tkasarla_ @WiCVworkshop @FidlerSanja @dlarlus Thank you for listening 😊

0

0

4