Yuki @ ICLR'24 @y_m_asano Twitter profile | Pikagi

Pikagi

Yuki @ ICLR'24

@y_m_asano

3,422

Followers

688

Following

130

Media

497

Statuses

Assistant Professor for Computer Vision and Machine Learning at the QUVA Lab, @UvA_Amsterdam . Previously @Oxford_VGG , @OxfordAI , interned @facebookai

https://t.co/ClqOcI9Bos

Joined July 2014

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

Pinned Tweet

@y_m_asano

Yuki @ ICLR'24

17 days

Check out our @CVPR paper on making caption-based Vision-Language Models do object-localization without _any_ human-supervised detection data! ⁉️ We develop a new *VLM-specific PEFT method* 🤩which is more powerful than LoRA etc. We test on non-training categories only!

Tweet media one

@mdorkenw

Michael Dorkenwald

17 days

How can one easily teach caption-pretrained VLMs to localize objects? We show that a small Positional Insert (PIN) can unlock object localization abilities without annotated data on frozen autoregressive VLMs. #CVPR2024 📝: 🌐:

Tweet media one

1

21

96

1

11

80

Last Seen Profiles

@CarmenLagala

@dolcelunee

@guessimluis

@BethFisherSport

@DIRECTVChile

@steveubl

@KossDaBoss27

@retrograth

@SeaGullFootball

@biomejs

@BrofftFans

@nazaneentv

@tvtmwtw

@lernajs

@Collateralnwk

@HPChain_AI

@neilsonfrance

@ssr_tag

@muypauly

@EvanMarkham4

@ohdiaval

@rumney_rfc

@BryceDShook

@vintagemenace

@PKERRIGAN2

@tessthemesssss

@sivaramansiraki

@Drstevenhobbs

@stones_tv

@BonziWells

@TheLondonGroup

@doublebunny_koo

@NwagbaraIzuchuk

@NNUBaseball

@Teppsta9

@jbmp51

@y_m_asano

Yuki @ ICLR'24

2 years

We computer vision researchers rarely look at the individual data points inside our datasets. Mainly because we are too lazy and/or do not have the right tools. This needs to change. And now we have a great tool from @TensorFlow datasets team: Know Your Data. A thread.🧵(1/5)

6

131

734

@y_m_asano

Yuki @ ICLR'24

4 months

Very happy to announce that VeRA is accepted at @iclr_conf with scores 8,8,8,5! VeRA makes LoRA ~10x more parameter efficient while retaining the same performance & also works for vision! Paper: Our very light-weight webpage😏:

Tweet media one

@_akhaliq

AK

7 months

VeRA: Vector-based Random Matrix Adaptation paper page: Low-rank adapation (LoRA) is a popular method that reduces the number of trainable parameters when finetuning large language models, but still faces acute storage challenges when scaling to even…

Tweet media one

6

62

269

14

121

659

@y_m_asano

Yuki @ ICLR'24

3 years

Today we @Oxford_VGG release the dataset 𝐏𝐀𝐒𝐒: 1.4M, CC-BY licensed images that do not depict humans, human parts or other PID. It can be used for self-supervised pretraining and works as well as ImageNet. info & models: paper:

@_akhaliq

AK

3 years

PASS: An ImageNet replacement for self-supervised pretraining without humans pdf: abs:

Tweet media one

4

33

152

5

82

330

@y_m_asano

Yuki @ ICLR'24

2 years

Missed the QUVA Deep Vision lecture by Dr. Andreas Geiger ( @uni_tue , @MPI_IS ) yesterday? Here's his talk on "Neural Implicit Representations for 3D Vision and Beyond". You can also find other interesting talks from the past on our group's channel!

Tweet media one

Tweet media two

0

36

187

@y_m_asano

Yuki @ ICLR'24

2 years

Our 2nd workshop on "Self-supervised Learning - What is Next?" coming to next #ECCV22 ! More updates soon! In the meantime, checkout the previous iteration and marvel at how far we've come in SSL since then: Organised with @chrirupp @dlarlus A. Zisserman

2

18

180

@y_m_asano

Yuki @ ICLR'24

3 years

What comes now: I'm excited to say that today I start as an Assistant Professor at the QUVA lab at the University of Amsterdam 🎊. I'll be working with @cgmsnoek , @wellingmax , @egavves , @QCOMResearch and the many talented students here! Onwards!

@y_m_asano

Yuki @ ICLR'24

3 years

Just presented and successfully defended my D.Phil. to my examiners @phillip_isola and Philip Torr!🥳🎉 It was an honor and pleasure @Oxford_VGG with Andrea Vedaldi, @chrirupp and many amazing colleagues like @mandelapatrick_ and @afourast ! On to new adventures!

Tweet media one

21

3

176

20

3

176

@y_m_asano

Yuki @ ICLR'24

3 years

Just presented and successfully defended my D.Phil. to my examiners @phillip_isola and Philip Torr!🥳🎉 It was an honor and pleasure @Oxford_VGG with Andrea Vedaldi, @chrirupp and many amazing colleagues like @mandelapatrick_ and @afourast ! On to new adventures!

Tweet media one

21

3

176

@y_m_asano

Yuki @ ICLR'24

2 years

Yesterday I gave my first lecture for the @UvA_IvI Deep Learning 1 course at @Lab42UvA . Extremely happy for the great team of TAs (lead by Christos Athanasiadis and @phillip_lippe ) and super motivated to make the students self-sufficient deep learners! 🌐:

Tweet media one

2

18

171

@y_m_asano

Yuki @ ICLR'24

1 year

Getting excited for my "Self-supervised and Vision-Language Learning" lectures starting tomorrow for the @UvA_IvI 's MSc in AI, Deep Learning 2 course: Sharing a preview in @CSProfKGD style :) Soo much recent progress, learned a lot in preparing it.😊

3

29

163

@y_m_asano

Yuki @ ICLR'24

1 year

Since everyone only tags these when things go wrong.. Great job @overleaf and @openreviewnet 👏🎉! Submitting just a few minutes before @CVPR deadline worked without any problems!! I do wonder how many GB they get in the final minutes/seconds 🤔..

3

13

147

@y_m_asano

Yuki @ ICLR'24

4 years

Our recordings are online 🎉! Listen to the talks from our Self-Supervised Learning workshop at #ECCV2020 you've missed here: and find slides at . Thanks again to all speakers and participants!

Tweet card media

Self-Supervised Learning - What is Next? - Workshop at ECCV 2020, August 28th

www.youtube.com

@y_m_asano

Yuki @ ICLR'24

4 years

Looking forward to the Self-Supervised Learning Workshop we’ve organized with @chrirupp , A. Vedaldi and A. Joulin at #ECCV2020 . Join us tomorrow for our speakers: @avdnoord , P. Favaro, @CarlDoersch , A. Zisserman, I. Misra, S. Yu, A. Efros, @pathak2206 ! .

Tweet media one

2

33

108

2

48

144

@y_m_asano

Yuki @ ICLR'24

1 year

Really cool work I finally read now: Learning to Discover and Detect Objects by @tvlfom , @Ismail_Elezi D. Ramanan @lealtaixe @AljosaOsep Nice application of SSL+supervised tools for novel class obj detection. And: cool that SeLa's SK makes it work😀💪 📄:

Tweet media one

2

24

123

@y_m_asano

Yuki @ ICLR'24

4 months

Check out our @iclr_conf [oral] paper on learning state-of-the-art ViTs from a single video from scratch! One of the coolest things is that multi-object tracking emerges from the different heads in the plain ViTs (three heads visualised below in R,G,B).

@shawshank_v

Shashank @ ICLR'24

4 months

Really happy to share that DoRA is accepted as an Oral to @iclr_conf #ICLR2024 Using just “1 video” from our new egocentric dataset - Walking Tours, we develop a new method that outperforms DINO pretrained on ImageNet on image and video downstream tasks. More details in 🧵👇

2

20

116

2

16

123

@y_m_asano

Yuki @ ICLR'24

2 years

Looking forward to giving a talk on self-supervised learning -- the data, using multi-modal data and leveraging augmentations at @QCOMResearch in San Diego. @egavves @m_hofmann

Tweet media one

2

3

116

@y_m_asano

Yuki @ ICLR'24

11 months

🎉! I have a new opening: PhD position on "Adaptable Foundation Models". Joint-supervised with @cgmsnoek and integrated into the Qualcomm-UvA Lab within the diverse AI environment of Amsterdam, you will conduct boundary-shifting, out-the-box research. 🌐:

PhD Position on Adaptable Foundation Models

PhD Position on Adaptable Foundation Models

vacatures.uva.nl

0

32

115

@y_m_asano

Yuki @ ICLR'24

4 years

Looking forward to the Self-Supervised Learning Workshop we’ve organized with @chrirupp , A. Vedaldi and A. Joulin at #ECCV2020 . Join us tomorrow for our speakers: @avdnoord , P. Favaro, @CarlDoersch , A. Zisserman, I. Misra, S. Yu, A. Efros, @pathak2206 ! .

Tweet media one

2

33

108

@y_m_asano

Yuki @ ICLR'24

1 year

With @iclr_conf done & @NeurIPSConf deadline rapidly approaching, here's something to look forward to 🤩: Our workshop @ICCVConference : "🍔BigMAC: Big Model Adaptation for Computer Vision" with amazing speakers 🌐: 📆: 2nd October 9am-1pm, details soon

Tweet media one

1

22

99

@y_m_asano

Yuki @ ICLR'24

4 years

🎉We open-sourced the code and models to our #NeurIPS2020 SeLaVi ("Labelling unlabelled videos from scratch with multi-modal self-supervision") paper! Joint w/ @mandelapatrick_ , @facebookai , @chrirupp , VGG Cluster your own videos or explore our clusters!

Tweet media one

Tweet media two

1

20

100

@y_m_asano

Yuki @ ICLR'24

7 months

Reminder from Bill Freeman at the Quo Vadis workshop that it's not the quantity but that _one_ creative/weird paper that matters.

Tweet media one

2

12

90

@y_m_asano

Yuki @ ICLR'24

2 years

This week marks my one year anniversary of being assistant prof at the @UvA_Amsterdam . 🥳🎉 To celebrate this, I want to share a few of my distilled reflections.

1

0

90

@y_m_asano

Yuki @ ICLR'24

6 months

🎉! Today's the start of our Deep Learning 1 course at the @UvA_IvI MSc in AI. Excited to introduce a new cohort of ~200 students to the intricacies, nitty-gritty details and mysteries of deep learning together with an amazing team of TAs:

Tweet media one

Tweet media two

Tweet media three

Tweet media four

2

4

89

@y_m_asano

Yuki @ ICLR'24

2 years

Visit our ICLR poster "Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing" with @irolaina and A. Vedaldi, from @Oxford_VGG . We linear-probe SSL models, but in ǝsǝʌǝɹ!🤯 For better interpretability. in 1h:

Tweet media one

Tweet media two

1

10

89

@y_m_asano

Yuki @ ICLR'24

7 months

So that's what it feels like if your PhD student gives an oral presentation in front of hundreds of researchers at @ICCVConference 🥹. Great job, Pengwan!

Tweet media one

Tweet media two

@y_m_asano

Yuki @ ICLR'24

7 months

Final day at @ICCVConference ! We have one oral at around 9:20am: "Self-ordering Point Clouds" where we learn how to select the most informative points with hierarchical contrastive learning (subsets as positive augmentations) and use Sinkhorn-Knopp for differentiable sorting.

Tweet media one

Tweet media two

1

4

34

0

4

83

@y_m_asano

Yuki @ ICLR'24

2 months

New preprint! LLM-to-SLM: let the big LM "think" (1x forward) and the small LM write (Nx forwards). simply idea and also shows Encoder LM are still super useful.

Tweet media one

@avskliar

Andrii Skliar 🇺🇦

2 months

🚀 Excited to share our latest work "Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding" now on arXiv! We're taking strides in making language models faster & more efficient on text generation tasks like translation & summarization.🔍 []

2

15

53

0

9

82

@y_m_asano

Yuki @ ICLR'24

6 months

CVPR ids are in the 15k range now...

4

8

82

@y_m_asano

Yuki @ ICLR'24

2 years

Come to our ECCV workshop (Hall C) from 9am: "Self-supervised Learning: What is Next?". We have a great line-up of speakers including: @jalayrac , @mcaron31 , @NagraniArsha , @imisra_ , Linda Smith and Andrea Vedaldi, and we start our series at 9:20am with Alyosha Efros!

Tweet media one

Tweet media two

4

11

77

@y_m_asano

Yuki @ ICLR'24

2 years

I like that SSL ideas are getting simpler again.

@_akhaliq

AK

2 years

SimMIM: A Simple Framework for Masked Image Modeling abs: When applied on a larger model of about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data

Tweet media one

2

40

195

4

7

75

@y_m_asano

Yuki @ ICLR'24

4 months

🤩🤩 Extremely happy to announce our ELLIS PhD school in Amsterdam: bringing together amazing researchers from all things foundation / large-scale / multi-modal / self-supervised AI! If you're a PhD student, don't miss this opportunity, it's straight after the @eccvconf deadline

@Ellis_Amsterdam

ELLIS Amsterdam

@Ellis_Amsterdam

4 months

📣From LLMs, LSTMs and Gemini, to Diffusion, VLMs and NeRF: join our ELLIS Winter School on Foundation Models in Amsterdam!✨ 🚀 ❄️ 📅 March 12-15, 2024 📍 @UvA_IvI 🌐 #AI #ML #ELLISforEurope @ELLISforEurope @ai_elise @UvA_Amsterdam #winterschool

Tweet media one

4

26

122

2

15

69

@y_m_asano

Yuki @ ICLR'24

2 years

Today, my friend & collaborator @TengdaHan sent me this: I've arrived at 1000 citations! 🥳 Or rather, the works I've co-authored with many brilliant & inspiring individuals, have, collectively reached a nice arbitrary number! Still: 🥳🎉! To celebrate: here's some TL;DRs

Tweet media one

6

0

68

@y_m_asano

Yuki @ ICLR'24

7 months

Join us for the 🍔BigMAC workshop on Big Model Adaptation in Computer Vision with our great line-up of speakers: @neilhoulsby @JMarakiii @cvondrick @lschmidt3 @imisra_ @AdtRaghunathan @RisingSayak ⏰ 9am - 1pm 📍 S03 🌐 ℹ️

Tweet media one

2

12

65

@y_m_asano

Yuki @ ICLR'24

1 year

I've learned a lot about equivariances and geometric deep learning for preparing today's lecture on graph neural networks. Still so much to learn, it's great!📚🤓

Tweet media one

Tweet media two

0

2

66

@y_m_asano

Yuki @ ICLR'24

7 months

We've now released the @ICCVConference 's BigMAC workshop recording: Also: most of the speakers' slides are now on the website too (and we're chasing the remaining ones) :).

Tweet media one

@y_m_asano

Yuki @ ICLR'24

7 months

Join us for the 🍔BigMAC workshop on Big Model Adaptation in Computer Vision with our great line-up of speakers: @neilhoulsby @JMarakiii @cvondrick @lschmidt3 @imisra_ @AdtRaghunathan @RisingSayak ⏰ 9am - 1pm 📍 S03 🌐 ℹ️

Tweet media one

2

12

65

0

16

67

@y_m_asano

Yuki @ ICLR'24

2 years

Don't forget to apply to this PhD vacancy🎓! We will work on exciting topics related to computer vision / self-supervised learning and video! We prioritize diversity and are committed to creating an inclusive environment for everyone. 📅 Deadline is 31st Jan.

@y_m_asano

Yuki @ ICLR'24

2 years

We have a PhD vacancy in the QUVA Lab 🎉! If you want to work with me and @cgmsnoek on pushing the frontier of SSL and video learning check this out!! :)

1

12

44

1

12

65

@y_m_asano

Yuki @ ICLR'24

1 year

Here's the (re-)recording of lecture 1 + updated slides: 🎥: 📄: Also, checkout the other cool modules of the DL2 course: from @egavves , @saramagliacane , @erikjbekkers , @eric_nalisnick , @wilkeraziz

Tweet card media

DL2: Self-supervised and vision-language learning (Lecture 1/2)

First lecture of the Self-supervised and vision-language learning module of the Deep Learning II course of the University of Amsterdam.Speaker: Dr. Yuki M. A...

www.youtube.com

@y_m_asano

Yuki @ ICLR'24

1 year

Getting excited for my "Self-supervised and Vision-Language Learning" lectures starting tomorrow for the @UvA_IvI 's MSc in AI, Deep Learning 2 course: Sharing a preview in @CSProfKGD style :) Soo much recent progress, learned a lot in preparing it.😊

3

29

163

0

16

65

@y_m_asano

Yuki @ ICLR'24

2 months

Day 2. Starting with @chrirupp from @Oxford_VGG . From Lucas-Kanade to epipolar geometry to tracking to open vocabulary segmentation to leveraging generative augmentations. A whirlwind of fundamentals and state-of-the-art! 👏

Tweet media one

Tweet media two

Tweet media three

Tweet media four

2

2

63

@y_m_asano

Yuki @ ICLR'24

2 months

@Ellis_Amsterdam ELLIS Winter school on Foundation Models kicking off! Happy to have a super diverse students with us in Amsterdam. @ELLISforEurope

Tweet media one

Tweet media two

Tweet media three

1

9

60

@y_m_asano

Yuki @ ICLR'24

1 year

Full house at the practical of our SSL + vision-language module! Want to follow along? Find the collab notebook made by my fabulous TAs @ivonajdenkoska and @mmderakhshani here 💻: lecture 2 📺: slides 📄:

Tweet media one

Tweet media two

Tweet media three

@y_m_asano

Yuki @ ICLR'24

1 year

Here's the (re-)recording of lecture 1 + updated slides: 🎥: 📄: Also, checkout the other cool modules of the DL2 course: from @egavves , @saramagliacane , @erikjbekkers , @eric_nalisnick , @wilkeraziz

0

16

65

0

11

56

@y_m_asano

Yuki @ ICLR'24

2 years

That's a wrap! 🎉 Thanks @visumschool for inviting us and thanks to the participants for their great questions to our session "Self-supervised learning for computer vision from images, video and audio. The why & how". With @TengdaHan from @Oxford_VGG .

Tweet media one

1

5

55

@y_m_asano

Yuki @ ICLR'24

2 months

Wrap-up of day 2 at our @ELLISforEurope winter school on Foundation Models: our poster session with drinks and Dutch borrel! Seriously strong research here. Also check out our amazing t-shirts :)

Tweet media one

Tweet media two

Tweet media three

1

4

53

@y_m_asano

Yuki @ ICLR'24

1 year

A little late, but here's a quick thread of one of my two @iclr_conf accepted papers! "The augmented image prior: Distilling 1000 classes by extrapolating from a single image", joint work with @aaqib_saeed @TUeindhoven 🌐: 🔖:

Tweet media one

1

6

53

@y_m_asano

Yuki @ ICLR'24

8 months

Finally it's out! 🎉 Our new work on leveraging the passage of time in videos for learning better image encoders. Big improvements for spatial tasks like unsupervised object segmentation. Check out the great thread below! Paper @ICCVConference

@MrzSalehi

mrz.salehi

8 months

New paper on exploring the power of videos for learning better image encoders 🎥🧠. Introducing "TimeTuning", a self-supervised method that tunes models on the temporal dimension, enhancing their capabilities for spatially dense tasks, such as unsupervised semantic segmentation.

3

20

85

0

6

53

@y_m_asano

Yuki @ ICLR'24

1 month

LoReFT is very interesting and follows our line of work in VeRA (ICLR'24) of making PEFT methods _much_ more parameter-efficient. Added their numbers in our table so you can compare it against other methods in one overview.

Tweet media one

@arankomatsuzaki

Aran Komatsuzaki

@arankomatsuzaki

1 month

ReFT: Representation Finetuning for Language Models 10x-50x more parameter-efficient than prior state-of-the-art parameter-efficient fine-tuning methods repo: abs:

Tweet media one

6

99

504

2

9

54

@y_m_asano

Yuki @ ICLR'24

1 year

Now at @iclr_conf ! If you're also here and want to have a chat, just ping me! :) if you don't know me, I mostly work on self-supervised and multi-modal learning and love to meet new people. 👋

Tweet media one

1

0

52

@y_m_asano

Yuki @ ICLR'24

1 year

What are important concepts that are hard to understand when encountering VAEs for the first time? What do you wish you would've been told/taught about this?

18

2

45

@y_m_asano

Yuki @ ICLR'24

2 years

Check out our new work on causal representation learning to appear in ICML'22! This thread↓ nicely summarizes our contributions.

@phillip_lippe

Phillip Lippe @ICLR2024

2 years

Happy to finally share our #ICML2022 paper "CITRIS: Causal Identifiability from Temporal Intervened Sequences". We investigate causal representation learning for multidimensional variables, and introduce the concept of "minimal causal variables". 🧵 1/11

Tweet media one

3

34

146

0

13

46

@y_m_asano

Yuki @ ICLR'24

2 months

And following up on this, we have @Thom_Wolf from @huggingface teaching us how to train LLMs with all the nitty gritty details. And the strong message to focus and inspect THE DATA. Also, second speaker in a row referring to @karpathy 's tokenizer lecture 🎏.

Tweet media one

Tweet media two

Tweet media three

3

6

47

@y_m_asano

Yuki @ ICLR'24

1 year

Last week we had two Guest Lectures in our Deep Learning course: A. Vedaldi from @Oxford_VGG on Learning 3D Geometry and @AmlabUva 's @wellingmax on AI4Science. Students saw previous concepts like GNNs, AEs, ViTs & self-sup. learning applied to two radically different topics. 🤩

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

2

47

@y_m_asano

Yuki @ ICLR'24

2 years

I will be giving a public talk about some of my research tomorrow as part of the QUVA Deep Vision lecture. It'll be about self-supervised learning and privacy/ethics in CV (SeLa, PASS, SeLaVi, GDT and our GPT-2 bias paper). Tune in here:

0

8

45

@y_m_asano

Yuki @ ICLR'24

3 years

Some news: In our new paper @PNASNews we show that a simple, agent-based macro-economic model where agents act myopically, can exhibit business-cycle like dynamics and near long-term economic optimality

Tweet card media

Emergent inequality and business cycles in a simple behavioral macroeconomic model | Proceedings of...

Standard macroeconomic models assume that households are rational in the sense that they are perfect utility maximizers and explain economic dynami...

2

8

42

@y_m_asano

Yuki @ ICLR'24

2 years

We have a PhD vacancy in the QUVA Lab 🎉! If you want to work with me and @cgmsnoek on pushing the frontier of SSL and video learning check this out!! :)

@cgmsnoek

Cees Snoek

2 years

📢 #PhD #Vacancy Alert: Self-Supervised Video Learning w/ @y_m_asano @UvA_Amsterdam #QUVA Lab. #CVPR #ICLR

1

19

69

1

12

44

@y_m_asano

Yuki @ ICLR'24

2 years

Using KYD, it's easy to explore our common computer vision datasets and analyse them in various dimensions. Here, I show you some things I played around with: For example, we can use meta-data and show images with high latitude: (2/5)

Tweet media one

Tweet media two

1

4

41

@y_m_asano

Yuki @ ICLR'24

4 months

Checkout our paper on making plain ViTs faster and better (supervised and SSL training), now accepted at @iclr_conf . Was very fun co-supervising the project during your internship @shawshank_v :)

@shawshank_v

Shashank @ ICLR'24

4 months

Delighted to share that SkipAT has been accepted to #ICLR2024 @iclr_conf This work was done as part of my internship at @QCOMResearch together with some amazing researchers - Amir Ghodrati, @y_m_asano , Fatih and @amir_habibian . Please check the thread 👇 for more details.

2

2

34

0

2

43

@y_m_asano

Yuki @ ICLR'24

2 years

Our #ECCV2022 @eccvconf workshop on self-supervised learning and its many new forms. This time with a call for papers with a deadline conveniently after ECCV decisions. Check it out ☑️ and share🔀!

@dlarlus

Diane Larlus

2 years

📢 Call for papers #ECCV2022 workshop 📢 *Self-supervised Learning - What is Next?* Submission deadline: July 6th More info:

Tweet media one

1

18

89

0

4

42

@y_m_asano

Yuki @ ICLR'24

2 years

After having served as an Area Chair for ECCV'22 – I am honoured to say that I look forward to AC'ing also for CVPR'23! 🚀 📖

0

0

39

@y_m_asano

Yuki @ ICLR'24

7 months

It's so nice to have a community of amazing kind people that you always feel welcome at :)

@NagraniArsha

Arsha Nagrani

7 months

VGG + ex-VGG catch up at @ICCVConference ! So many people that we needed to do a panorama to get everybody in :-) Missing the lab 😭 @Oxford_VGG #ICCV2023

Tweet media one

3

15

162

0

0

38

@y_m_asano

Yuki @ ICLR'24

2 months

Last day of our @ELLISforEurope FOMO winter school starting with a big 💥: @wellingmax on fluids and representations and the huge potential impact of AI in science. Immediately his first slide is best explanation of free energy I've heard (and I studied physics!)

Tweet media one

Tweet media two

Tweet media three

Tweet media four

3

3

36

@y_m_asano

Yuki @ ICLR'24

6 months

Cheesy talk titles: yes or no? @Ellis_Amsterdam symposium.

Tweet media one

0

0

36

@y_m_asano

Yuki @ ICLR'24

5 months

Hire this guy! He's a great researcher and engineer and working with him is fun! He's also the first author of our super cool and fun "1 video SSL learning" paper, where we beat imagenet DINO models by training on 1 video from scratch. 👀

Tweet card media

Is ImageNet worth 1 video? Learning strong image encoders from 1...

Self-supervised learning has unlocked the potential of scaling up pretraining to billions of images, since annotation is unnecessary. But are we making the best use of data? How more economical...

@shawshank_v

Shashank @ ICLR'24

5 months

Hi everyone, I am graduating early next year with a PhD from @Inria in AI. I am looking for an industrial research position and would appreciate your support. Thank you in advance for any connections, advice, or opportunities you can offer. My profile:

1

13

54

1

0

35

@y_m_asano

Yuki @ ICLR'24

1 year

Research -> meeting friends! 🥳 After speaking at Bristol's Machine Learning and Vision group of @dimadamen and having exciting discussions about research yesterday, I was happy to see old and new colleagues from @Oxford_VGG at my talk at @oxengsci in Oxford today.

0

0

35

@y_m_asano

Yuki @ ICLR'24

7 months

Final day at @ICCVConference ! We have one oral at around 9:20am: "Self-ordering Point Clouds" where we learn how to select the most informative points with hierarchical contrastive learning (subsets as positive augmentations) and use Sinkhorn-Knopp for differentiable sorting.

Tweet media one

Tweet media two

1

4

34

@y_m_asano

Yuki @ ICLR'24

1 year

Aaand like that, using Sinkhorn-Knopp (+++) for SSL is back to being the SOTA! @CuturiMarco

@_akhaliq

AK

1 year

DINOv2: Learning Robust Visual Features without Supervision train a ViT model with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP on most of the benchmarks at image and pixel levels abs:…

Tweet media one

4

143

732

1

3

33

@y_m_asano

Yuki @ ICLR'24

1 year

Happy to share with you the QUvA Deep Vision Seminar talk from @olivierhenaff from @DeepMind on "The virtuous cycle of object discovery and representation" is now online: Enjoy😊:

Tweet card media

The virtuous cycle of object discovery and representation by Dr....

Content:00:00 - Intro & Bio01:16 - Principles of biological and artificial intelligence16:36 - Efficient visual pretraining with contrastive detection29:50 -...

www.youtube.com

0

2

32

@y_m_asano

Yuki @ ICLR'24

4 years

I'm super happy to say that this unsupervised labelling of videos paper (via SSL-clustering and SK-optimal transport) with @mandelapatrick_ , @chrirupp and Andrea Vedaldi got accepted at #NeurIPS2020 ! 🎊🎊

@y_m_asano

Yuki @ ICLR'24

4 years

Really happy to share our new work on arXiv! do check out our interactive cluster visualization here:

3

3

24

1

3

31

@y_m_asano

Yuki @ ICLR'24

2 years

I'm sure that if we had this tool earlier, efforts like ImageNet-blurred, removing the person-subtree and PASS would've happened earlier. We don't have an excuse anymore to not see the bias and problems in our datasets. (5/5)

3

3

29

@y_m_asano

Yuki @ ICLR'24

7 months

Fixing outlier issues caused by softmaxes in transformers with three different solutions: a) add Gates b) clip values c) add "+1" in the soft a denominator. Cool talk from @TiRune at the LBQNN workshop. Perhaps "register tokens" another solution even.

Tweet media one

1

8

30

@y_m_asano

Yuki @ ICLR'24

5 months

Gathering a list of topics for our Foundation/Big Models course @UvA_IvI in the spring, that I'll be teaching together with @cgmsnoek . Besides the list below, what should we include?

Tweet media one

3

5

29

@y_m_asano

Yuki @ ICLR'24

1 year

This week we had our winter holidays dinner at the QUvA lab! It was an exciting year with many new challenges, collabs, success and growth for all of us. So some light-hearted time with good food was perfect😋. @cgmsnoek @egavves @phillip_lippe @eeevgen @mdorkenw @_gabrielecesa_

Tweet media one

1

1

29

@y_m_asano

Yuki @ ICLR'24

2 years

Visit our poster at the @NeurIPSConf Datasets and Benchmarks session now for the next two hours:

@y_m_asano

Yuki @ ICLR'24

3 years

Today we @Oxford_VGG release the dataset 𝐏𝐀𝐒𝐒: 1.4M, CC-BY licensed images that do not depict humans, human parts or other PID. It can be used for self-supervised pretraining and works as well as ImageNet. info & models: paper:

5

82

330

1

4

29

@y_m_asano

Yuki @ ICLR'24

3 months

Ended up being >600 applications.🤯 Now: keep checking your inboxes, we're sending acceptances continuously and will keep doing so ( spaces open due to visa issues etc.). See you all in Amsterdam @Ellis_Amsterdam , @Lab42UvA ! Huge thanks to co-organisers @pranindiati & @cgmsnoek

@Ellis_Amsterdam

ELLIS Amsterdam

@Ellis_Amsterdam

3 months

⏱ 3 days left to apply for the ELLIS Winter School on Foundation Models! 👉🏻 Check out the school & submit your application NOW: (speakers list and schedules have been recently updated!) 👀 We aim to have participants from highly diverse backgrounds

1

8

28

0

3

28

@y_m_asano

Yuki @ ICLR'24

1 year

Great point 👇. Also research is a bit like hiking in unknown terrain: you don't know the map at the beginning, you build it by exploring; still you never know if the trail doesn't suddenly stop. Plus, in AI research the terrain changes every 6months 😅

@CSProfKGD

Kosta Derpanis

1 year

Research is where failure is the norm. Don’t let social media posts convince you otherwise. Managing failure is an important skill to develop.

9

43

421

1

3

28

@y_m_asano

Yuki @ ICLR'24

2 years

Our paper on causal representation learning from videos got accepted into ICML. 🍋🎉 while we use toy datasets this is a great step for the future of representation learning.

@egavves

Efstratios Gavves

2 years

Great way to wake on a Sunday, our work on Causal Representation Learning from Temporal Intervened Sequences, w @phillip_lippe @TacoCohen @y_m_asano @saramagliacane @sindy_loewe accepted in #icml2022 ! 2 very good papers rejected, more for #neurips2022 😀

3

16

76

1

1

28

@y_m_asano

Yuki @ ICLR'24

7 months

Still some space in the room but getting cozy :) currently @neilhoulsby giving insights on ViTs

Tweet media one

Tweet media two

@y_m_asano

Yuki @ ICLR'24

7 months

Join us for the 🍔BigMAC workshop on Big Model Adaptation in Computer Vision with our great line-up of speakers: @neilhoulsby @JMarakiii @cvondrick @lschmidt3 @imisra_ @AdtRaghunathan @RisingSayak ⏰ 9am - 1pm 📍 S03 🌐 ℹ️

Tweet media one

2

12

65

0

3

28

@y_m_asano

Yuki @ ICLR'24

2 years

Very happy to be at the in-person @TheBMVA Symposium! Yesterday I was able to give a talk on our NeurIPS'21 oral Motionformer paper; get people excited about video data; and, importantly, meet many old ( @Oxford_VGG ) and new friends! Now day 2!

Tweet media one

1

0

27

@y_m_asano

Yuki @ ICLR'24

3 years

OK, I yield: Here's the happy news tweet: 2 papers accepted to @ICCV_2021 🎉 🎉 , joint work with @mandelapatrick_ and co. and @Oxford_VGG

1

2

27

@y_m_asano

Yuki @ ICLR'24

10 months

The last two weeks I had the pleasure and honor to travel in Ghana and Côte d'Ivoire and learn more about the countries and meet people. Particularly grateful for the opportunity to speak with folks @GoogleAI in Ghana @bapadadada and @UnivofGh w/ Jamal Deen.

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

0

26

@y_m_asano

Yuki @ ICLR'24

5 months

Super stoked and honored to be talking at the SSL workshop @NeurIPSConf tomorrow morning, alongside such amazing speakers. Will be bringing some Dutch paintings along!

Tweet media one

@TengdaHan

Tengda Han

5 months

Excited to advertise the "Self-Supervised Learning: Theory and Practice" workshop @NeurIPSConf 2023! 📍Room: 217 -- 219 ⏰Saturday, Dec 16 🔊Speakers: @y_m_asano @dlarlus Alyosha Efros, Abhinav Gupta @chelseabfinn @xinyun_chen_ 📄73 accepted papers, with 4 oral presentations

Tweet media one

3

13

42

0

1

25

@y_m_asano

Yuki @ ICLR'24

4 years

Had a great time chatting with @bhutanisanyam1 ! A pleasure and an honour! We talk about my recent research and my life as a PhD student in deep learning.

@bhutanisanyam1

Sanyam Bhutani

@bhutanisanyam1

4 years

More CV & cutting edge research interviews on @ctdsshow 🍵 In this ep, I interview @y_m_asano , PhD student @Oxford_VGG , @UniofOxford 🙏 We talk about Self-Supervision, Self-Labelling & CV Discussed Papers in thread Audio: Video:

Tweet media one

1

2

18

0

2

25

@y_m_asano

Yuki @ ICLR'24

4 years

Really happy to share our new work on arXiv! do check out our interactive cluster visualization here:

@Oxford_VGG

Visual Geometry Group (VGG)

4 years

Check out our new work "Labelling unlabelled videos from scratch with multi-modal self-supervision" by @y_m_asano @mandelapatrick_ @chrirupp and Andrea Vedaldi in colab with @facebookai ! See below for our automatically discovered clusters on VGG-Sound!

1

10

40

3

3

24

@y_m_asano

Yuki @ ICLR'24

5 months

This year I very much found that science isn't just doing research and papers! As area chair for CVPR/NeurIPS/ICLR/WACV & workshop organizer at ICCV/NeurIPS & via meeting friends of friends at conferences I learned: everyone can make their own community. Thanks for being in it!🥳

0

1

24

@y_m_asano

Yuki @ ICLR'24

1 year

It was such a nice event! Seeing friends and meeting new ones all the while seeing NeurIPS works -- and it being simply downstairs from my office is 💯 . Especially also super happy to see the mingling between PhD and MSc students and other researchers! 🙌

@Ellis_Amsterdam

ELLIS Amsterdam

@Ellis_Amsterdam

1 year

Happening now: the NeurIPS Fest 🎉 at @Lab42UvA over 100 people are here to see 38 poster presentations of the latest AI research in Amsterdam #ai #machinelearning #ELLISamsterdam

Tweet media one

0

8

40

1

1

24

@y_m_asano

Yuki @ ICLR'24

3 years

We got an oral at NeurIPS!! 🎊😋 In this work we developed a new attention mechanism specifically for vision transformers that work on (longer) videos. As always great and fun collab with @mandelapatrick_ et al.!

@mandelapatrick_

Mandela Patrick

@mandelapatrick_

3 years

Our work Motionformer was accepted as an ORAL at NeurIPS 2021! We present a novel trajectory-focused self-attention block, which essentially tracks space-time patches for video transformers. Work with amazing collaborators @facebookai @Oxford_VGG . Code:

2

14

97

1

1

24

@y_m_asano

Yuki @ ICLR'24

7 months

Now @RisingSayak from @huggingface giving a great overview, insights and limitations into controlling Text-to-Image generative models. Solutions at low compute. Token inversion, controlnet, attend & excite etc.

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

1

23

@y_m_asano

Yuki @ ICLR'24

2 years

Or we can sort the dataset by number of "detected" faces. Here's PASS: Here's ImageNet: (I will not link to other problematic human-containing pictures in ImageNet, but please, as a researcher, explore a bit.) (4/5)

Tweet media one

Tweet media two

2

2

22

@y_m_asano

Yuki @ ICLR'24

2 months

Start of day 3 of our @Ellis_Amsterdam winter school. Starting with @TimSalimans from @Google on image and video generation with diffusion models. From basics to sota 1-4 step generation methods. 👌

Tweet media one

Tweet media two

Tweet media three

1

1

23

@y_m_asano

Yuki @ ICLR'24

4 months

Another cool LLM paper accepted to @iclr_conf ! This time on structured pruning for LLMs without losing much performance. Work done by @tychovdo who did his internship @QCOMResearch Amsterdam -- was very fun to help out! Check the informative thread below 👇

@tychovdo

Tycho van der Ouderaa

4 months

⭐️New paper ⭐️ Excited to share 'The LLM Surgeon', accepted at ICLR 2024. We obtain SOTA pruning performance and even demonstrate structured LLM pruning of full rows and cols. Direct practical impact enabling compression up to 20-30% with negligible loss in performance.🧵1/9👇

Tweet media one

3

13

108

0

2

22

@y_m_asano

Yuki @ ICLR'24

7 months

Alyosha: "not saying we need to move back to kNN, but.." [a) we should focus on data over algorithms b) think about what comes after copying, intelligence as emergent phenomenon c) self supervised learning and data gen for robotics]

Tweet media one

0

1

22

@y_m_asano

Yuki @ ICLR'24

5 months

🤯 "across a large number of TPUv4 pods across multiple data centers from a single Python process."

@JeffDean

Jeff Dean (@🏡)

5 months

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks,…

Tweet media one

Tweet media two

276

3K

13K

1

1

22

@y_m_asano

Yuki @ ICLR'24

4 months

Wow!! We already have >240 applications for our ~100 spots! 🎉🎉 We're trying to increase capacity and decided to start sending acceptances on a rolling basis. We will still accept applications until the 15th Feb though, but this should help with visa/hotel booking. Go submit!🚀

@y_m_asano

Yuki @ ICLR'24

4 months

🤩🤩 Extremely happy to announce our ELLIS PhD school in Amsterdam: bringing together amazing researchers from all things foundation / large-scale / multi-modal / self-supervised AI! If you're a PhD student, don't miss this opportunity, it's straight after the @eccvconf deadline

2

15

69

0

1

21

@y_m_asano

Yuki @ ICLR'24

4 years

Finally got around to uploading some more pretrained torchvision resnet models for our SeLa method! NMI=76%, aNMI=53% and Linear probing of 68.8% simply by using the SimCLR augmentation - still just 280 epochs and linear head. SSL=augmentations. Enjoy!🎉

Tweet card media

GitHub - yukimasano/self-label: Self-labelling via simultaneous clustering and representation...

Self-labelling via simultaneous clustering and representation learning. (ICLR 2020) - yukimasano/self-label

1

3

21

@y_m_asano

Yuki @ ICLR'24

30 days

Very interesting! Also nice side insights on the Mistral model(s)!

@vaibhav_adlakha

Vaibhav Adlakha

@vaibhav_adlakha

1 month

We introduce LLM2Vec, a simple approach to transform any decoder-only LLM into a text encoder. We achieve SOTA performance on MTEB in the unsupervised and supervised category (among the models trained only on publicly available data). 🧵1/N Paper:

Tweet media one

14

162

852

0

4

21

@y_m_asano

Yuki @ ICLR'24

3 years

Small one but a good one! We test out whether object detection on COCO works with blurred and swapped faces: It does. Towards more private and less biased training of models! work with @OxfordAI .

Tweet media one

1

3

21

@y_m_asano

Yuki @ ICLR'24

5 months

Now is a good point to urge people to spend more effort in cleaning datasets and valuing that. I feel like in '21 with the first NeurIPS data there was momentum, but with LAION winning best paper in '22, my hope went down. Our SSL IN1-k alternative:

@samleecole

Samantha Cole

5 months

big breaking news: LAION just removed its datasets, following a study from Stanford that found thousands of instances of suspected child sexual abuse material

2

599

2K

0

1

21

@y_m_asano

Yuki @ ICLR'24

4 months

Was such a pleasure to participate in all the discussions with the other speakers @HildeKuehne and @frank_e_keller , the students and an honor (and pressure) to give a talk straight after Andrew Zisserman! 😁 Thx for Orga! @TengdaHan @mwray0 @davmoltisanti

@BMVCconf

British Machine Vision Conference (BMVC)

4 months

BMVA Symposium on Vision and Language One Day BMVA symposium in London, UK Wednesday, 17th January 2024 Chairs: Michael Wray (University of Bristol), Davide Moltisanti (University of Bath), and Tengda Han (University of Oxford).

0

6

16

1

1

21

@y_m_asano

Yuki @ ICLR'24

1 year

The Segment Anything model is great & I was happy to read that the SA-1B dataset is licensed and "privacy preserving"! Yet when I looked at the data for 10min, I found >8 imgs with faces unblurred. A reminder that making AI data private is not a finished task, let's keep going!💪

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

3

19

@y_m_asano

Yuki @ ICLR'24

3 months

Let's do more of this please :) -- also it works nicely

Tweet media one

2

0

20

@y_m_asano

Yuki @ ICLR'24

2 years

or images that have a "cat" and a "keyboard" in them: or boats and fireworks: (3/5)

Tweet media one

Tweet media two

1

1

18

@y_m_asano

Yuki @ ICLR'24

2 years

Glad to see self-supervised learning being named a core/foundational ingredient for learning the basics in vision!

Tweet media one

@cgmsnoek

Cees Snoek

2 years

Keynote by deep learning titan @HochreiterSepp at the Video Understanding Symposium at @UvA_Amsterdam #ELLIS

Tweet media one

1

7

69

1

1

20

@y_m_asano

Yuki @ ICLR'24

2 years

Last week, we were fortunate to have Prof. @dimadamen give an amazing talk about "Video Understanding - An Egocentric Perspective" at our QUVA lecture. The talk is now online on our channel: Find previous and future talks here:

Tweet media one

Tweet media two

Tweet media three

0

1

19

@y_m_asano

Yuki @ ICLR'24

1 month

Was super fun to organise and to meet so many great minds :)!

@ELLISforEurope

ELLIS

@ELLISforEurope

1 month

Applause for our #ELLISUnit @Ellis_Amsterdam , which hosted the ELLIS Winter School on #FoundationModels ! Supported by @ai_elise , the vibrant event provided an in-depth look into how Europe is guiding its own research agenda in this crucial field!

0

2

37

0

0

19

@y_m_asano

Yuki @ ICLR'24

1 year

It was a pleasure to give a talk @TampereUni this morning! Thanks @EsaRahtu for hosting :)

Tweet media one

@JoniKamarainen

Joni Kämäräinen

@JoniKamarainen

1 year

Meillä @TampereUni Signaalinkäsittely ja koneoppiminen -pääaineessa opiskelijat osallistuvat salaseuraan, jossa alansa asiantuntijat kertovat salaisuuksia tutkimuksestaan. Tänään Yuki Asano ( @y_m_asano ) from @UvA_Amsterdam

Tweet media one

0

0

7

0

1

18