Adrian Bulat

Research scientist at Samsung AI Cambridge, member of the deeplearning cult.

[Adrian Bulat @AdrianBulat]

Just a few days left (3rd of July) to submit your work on extreme quantization to the BiVision Workshop @ICCVConference We look forward to hear about you interesting work in this area! #ICCV2025

Call for papers: https://t.co/6IvhPdNuzx

[Adrian Bulat @AdrianBulat]

Only a few days left (1st of august) to submit your papers to the Low-Bit Quantized Neural Networks (LBQNN) workshop @ICCVConference ⌛️

[Adrian Bulat @AdrianBulat]

Join us at #iccv2023 at the workshop on Low-Bit Quantized Neural Networks (LBQNN). Learn about the latest developments in the field, foster collaborations or share your work by submitting a paper by 1st of august. Call for papers: https://t.co/oZMa1waCR6

[Adrian Bulat @AdrianBulat]

Join us at #iccv2023 at the workshop on Low-Bit Quantized Neural Networks (LBQNN). Learn about the latest developments in the field, foster collaborations or share your work by submitting a paper by 1st of august. Call for papers: https://t.co/oZMa1waCR6

[Samsung Research @samsungresearch]

[Tech Blog] #CVPR2023 series ⑥
Introducing LASP, a text-to-text optimization method for vision language adaptation that sets a new state-of-the-art for #fewshot and #zeroshot image classification.

#AI #VisionLanguage

https://t.co/ixvmMwhi6j

[Mohammad Mahdi (Medi) Derakhshani @mmderakhshani]

📢📢📢📢Check our new Arxiv paper: Variational Prompt Tuning Improves Generalization of Vision-Language Models
Link: https://t.co/sHbuSJ9EUA

w/ Enrique Sanchez, @AdrianBulat, @victorturrisi, @cgmsnoek, Georgios Tzimiropoulos, Brais Martinez at @samsungresearch
🧵1/5

[Adrian Bulat @AdrianBulat]

Our work "Bit-Mixer: Mixed-precision networks with runtime bit-width selection" has being accepted at #ICCV2021 @ICCV_2021 !

Check it out if want to learn more about how you can quantize your model's blocks to different bit-widths at runtime.

Preprint: https://t.co/rTr5bBINBA

[Adrian Bulat @AdrianBulat]

Code will be released soon, in the meantime you can check our mini-framework used to train the models:
https://t.co/CTqLykYC8Q

n/n

[Adrian Bulat @AdrianBulat]

If you want to find more about getting high performing binary networks using conditional computing pass by our poster session tomorrow at @iclr_conf

arxiv: https://t.co/GaFMblWp5g

1) Wider is better than deeper for BNNs, especially when combined with grouped convolutions.

1/n

[Adrian Bulat @AdrianBulat]

2) Dynamically selecting at runtime a single expert (i.e. weight) can boost the accuracy of Binary Networks at little additional computational cost.
3) Multi-staged approaches and feature-level distillation is necessary for high accuracy.

2/n

[Babak Taati @Babak_Taati]

Journal club today at 1:

We'll read "Pre-training strategies and datasets for facial representation learning" by @AdrianBulat et al.

@LeifSimmatis will be leading the discussion.

@KITETrainees
@AGEWELL_NCE
@TRI_UHN

https://t.co/zZ0GrcEymd

[Gautam Kamath @thegautamkamath]

In the past I've thought that having a comment system on arXiv would enable productive discussion and identification of errors in papers which were previously only known to a select few.

Based on #ICLR2021's OpenReview, I think it would just be people saying "plz cite me"

[Adrian Bulat @AdrianBulat]

Excited to announce the Workshop on Binary Networks held in conjunction with #CVPR2021. Great place for learning about efficient deep learning models from our amazing invited speakers. Paper submission will open soon.

For more details, please check: https://t.co/sGoMSDyQrM

[Jean Kossaifi @JeanKossaifi]

Interested in automatic #emotion estimation from faces in natural conditions? 😁☹️😠😧😮

Checkout our @NatMachIntell paper - we estimate discrete emotion, continuous valence & arousal levels and facial landmarks w/ very high accuracy! ⬇️
https://t.co/4doG4aiUw2 @SpringerNature

[EECVC @eecvc_conf]

Videos of #EECVC2020 are available!
Day 2: Dr. Daniel Barath talk "State of the art in robust geometry estimation"
and Dr. @AdrianBulat "Efficient deep models via network binarization/quantization"
https://t.co/gXJuOAusG1

[EECVC @eecvc_conf]

Videos of #EECVC2020 are available!
Day 1: Dr. @amy_tabb talk "Computer vision and robotics in agriculture"
and Dr. @ftmguney talk "Optical flow"
https://t.co/dopNt0K5TH

[Adrian Bulat @AdrianBulat]

@ducha_aiki Totally agree! Best email is the one you can actually access.
Same happened to me, my university email got terminated on the graduation day. Needless to say that now I have multiple accounts on pretty much all academic websites and get invites or spam on all of them :)

[Adrian Bulat @AdrianBulat]

@JeanKossaifi @JmlrOrg @zacharylipton @arinbjornkol @arankhanna @furlanel @AnimaAnandkumar Congratulations! Great work and an interesting paper to read!

[EECVC @eecvc_conf]

Today is the 2nd day of the #EECVC2020. Register now, if you haven't already, to listen to our speakers at 19:00 GMT+3
Adrian Bulat about CNN quantization and Dr. Daniel Barath about modern RANSACs!
https://t.co/LqEaGk3DgL

[Adrian Bulat @AdrianBulat]

@JeanKossaifi @nvidia @AnimaAnandkumar @NvidiaAI Congratulation! May the tensors be with you, and the luck too! :)

[Alona Fyshe (she/her) @alonamarie]

The #NeurIPS reviewer option “I will consider not reviewing for NeurIPS again if this submission is accepted.” is ridiculous. It encourages a toxic attitude towards reviewing, and when it is actually used, can be incredibly hurtful to our young scholars. @NeurIPSConf