André Araujo Profile
André Araujo

@andrefaraujo

Followers
305
Following
20
Media
9
Statuses
39

I'm a Research Scientist at Google DeepMind, working on computer vision and machine learning.

São Paulo, Brazil
Joined July 2009
Don't wanna be here? Send us removal request.
@andrefaraujo
André Araujo
2 months
We're hiring! 🚀 Our @GoogleDeepMind team is looking for a Research Engineer to help push the boundaries of Multimodal AI! This position is in Mountain View. We are looking for candidates who recently finished their PhDs, or have equivalent experience.
job-boards.greenhouse.io
0
0
6
@g_kordo
Giorgos Kordopatis-Zilos
5 months
🚨 Deadline Extension Instance-Level Recognition and Generation (ILR+G) Workshop at ICCV2025 @ICCVConference 📅 new deadline: June 26, 2025 (23:59 AoE) 📄 paper submission: https://t.co/gTGYhrTc6Z 🌐 ILR+G website: https://t.co/Oy1vGAg5uh #ICCV2025 #ComputerVision #AI
1
5
10
@andrefaraujo
André Araujo
5 months
Excited to share our TUNER paper tomorrow morning at #CVPR2025! Come find us at poster #278 during the morning session. BTW, see TUNER's code at:
github.com
Contribute to DianaPat/TUNER development by creating an account on GitHub.
@TiagoNovello
Tiago Novello
6 months
@andrefaraujo @DianaAldana97 @lvelho Excited to present our highlight paper TUNER tomorrow (June 13) at #CVPR2025! Come find us at poster #278 during the morning session—we’d love to chat and hear your thoughts. Code is available here: https://t.co/ygAZx6I6mQ.
0
0
5
@andrefaraujo
André Araujo
6 months
Talk starting at 10:45 AM in room 202 C! #CVPR2025
@andrefaraujo
André Araujo
6 months
What’s missing in Multimodal AI? Well… a lot of things! I’ll share some thoughts on this at the #CVPR2025 BEAM workshop on Wednesday ( https://t.co/RDn9r9uy7X). A few things I'll highlight: spatial awareness, effective tool use and fine-grained understanding. Please come by!
0
0
2
@andrefaraujo
André Araujo
6 months
What’s missing in Multimodal AI? Well… a lot of things! I’ll share some thoughts on this at the #CVPR2025 BEAM workshop on Wednesday ( https://t.co/RDn9r9uy7X). A few things I'll highlight: spatial awareness, effective tool use and fine-grained understanding. Please come by!
1
0
11
@g_kordo
Giorgos Kordopatis-Zilos
7 months
🚨 Call for Papers! 7th Instance-Level Recognition and Generation Workshop (ILR+G) at @ICCVConference 📍 Honolulu, Hawaii 🌺 📅 October 19–20, 2025 🌐 https://t.co/Oy1vGAg5uh in-proceedings deadline: June 7 out-of-proceedings deadline: June 30 #ICCV2025
1
5
10
@andrefaraujo
André Araujo
7 months
We'll be presenting TIPS today at #ICLR2025! Please come by poster 318 this morning to discuss with our team, looking forward to it!
0
0
7
@andrefaraujo
André Araujo
8 months
Google's global PhD Fellowship program will open for applications this week! (on Apr 10th) This supports PhD students in computer science and related fields, also connecting to a Google mentor. Learn more and apply at: https://t.co/ynVQDf5xLi (deadline: May 15th, 2025)
Tweet card summary image
research.google
0
1
5
@andrefaraujo
André Araujo
8 months
Multimodal AI encoders often lack spatial understanding… but not anymore! Our #ICLR2025 TIPS model (Text-Image Pretraining with Spatial awareness) from @GoogleDeepMind can help 💡🚀 Check out our strong & versatile image-text encoder 💪 Paper & code: https://t.co/LCiqV4gaQ0
6
68
328
@andrefaraujo
André Araujo
9 months
Excited to release a super capable family of image-text models from our TIPS #ICLR2025 paper! https://t.co/1scX7H1DIb We have models from ViT-S to -g, with spatial awareness, suitable to many multimodal AI applications. Can’t wait to see what the community will build with them!
Tweet card summary image
github.com
Contribute to google-deepmind/tips development by creating an account on GitHub.
@andrefaraujo
André Araujo
1 year
Want some TIPS? Well, then check out “Text-Image Pretraining with Spatial awareness” :) TIPS is a general-purpose image-text encoder, for off-the-shelf dense and image-level prediction. Finally image-text pretraining with spatially-aware representations! https://t.co/LCiqV4gaQ0
1
6
16
@andrefaraujo
André Araujo
9 months
Happy to share our #CVPR2025 paper on robust training for sinusoidal neural networks! Our theoretical insights shed light on the capacity of these models, being directly useful to improve their training. https://t.co/9PCQkYJh3Y with @TiagoNovello, @DianaAldana97, @lvelho
1
9
40
@andrefaraujo
André Araujo
9 months
Very happy to see learnings from our TIPS method (ICLR'25 accepted https://t.co/IP6JowSDcE) adopted into SigLIP2! A very nice collaboration, great outcome!
Tweet card summary image
arxiv.org
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding...
@XiaohuaZhai
Xiaohua Zhai
9 months
Introducing SigLIP2: now trained with additional captioning and self-supervised losses! Stronger everywhere: - multilingual - cls. / ret. - localization - ocr - captioning / vqa Try it out, backward compatible! Models: https://t.co/3hOdqcy9QD Paper: https://t.co/Tp4D8Syld8
0
1
11
@andrefaraujo
André Araujo
1 year
Great work from our team at @GoogleDeepMind! With @kmaninis, @kfrancischen, @sohamg121, @arjunkarpur, Koert Chen, Ye Xia, Bingyi Cao, @GuangxingHan, Jan Dlabal, Dan Gnanapragasam, Mojtaba Seyedhosseini, @howardzzh
0
2
3
@andrefaraujo
André Araujo
1 year
Want some TIPS? Well, then check out “Text-Image Pretraining with Spatial awareness” :) TIPS is a general-purpose image-text encoder, for off-the-shelf dense and image-level prediction. Finally image-text pretraining with spatially-aware representations! https://t.co/LCiqV4gaQ0
4
11
50
@andrefaraujo
André Araujo
1 year
Starting soon! Don't miss Cordelia Schmidt's keynote at 9:10am! @CordeliaSchmid #ECCV2024
@andrefaraujo
André Araujo
1 year
#ECCV2024 Our Instance-Level Recognition workshop is tomorrow morning (Monday 9am at Amber 5)! Great keynotes (@CordeliaSchmid, @jampani_varun, @g_kordo), accepted papers and invited papers from the main conference. Don't miss it! https://t.co/9ztsdEqaao
0
0
2
@andrefaraujo
André Araujo
1 year
#ECCV2024 Our Instance-Level Recognition workshop is tomorrow morning (Monday 9am at Amber 5)! Great keynotes (@CordeliaSchmid, @jampani_varun, @g_kordo), accepted papers and invited papers from the main conference. Don't miss it! https://t.co/9ztsdEqaao
0
1
11
@andrefaraujo
André Araujo
1 year
Really happy to share that UDON was accepted into NeurIPS'24! Paper: https://t.co/YxdXHqg1nB Code: https://t.co/SlVJLn7UHB with @YpsilantisNikos, @kfrancischen, Ondra Chum
Tweet card summary image
github.com
Contribute to nikosips/UDON development by creating an account on GitHub.
@andrefaraujo
André Araujo
1 year
Excited to release UDON, our latest & greatest universal image embedding! Effective and efficient multi-teacher distillation to improve performance across different fine-grained domains. Code coming soon! https://t.co/trDeeyOXl7 with @YpsilantisNikos, @kfrancischen, Ondřej Chum
1
2
13
@andrefaraujo
André Araujo
1 year
And the ILR workshop's accepted papers are announced! We're happy to feature 2 long and 3 short papers on several relevant topics for our workshop: point tracking, image re-ranking, referring segmentation, etc See the accepted papers at
@andrefaraujo
André Araujo
1 year
One more week to go for the ILR workshop submission deadline at #ECCV2024! We welcome a broad range of topics in the area of instance-level recognition, with both short or long formats. Submit at:
0
1
6
@andrefaraujo
André Araujo
1 year
One more week to go for the ILR workshop submission deadline at #ECCV2024! We welcome a broad range of topics in the area of instance-level recognition, with both short or long formats. Submit at:
openreview.net
Welcome to the OpenReview homepage for ECCV 2024 Workshop ILR
@andrefaraujo
André Araujo
1 year
Announcing the #ECCV2024 workshop on Instance-Level Recognition (ILR)! This is the 6th edition in our workshop series, with amazing keynote speakers: @CordeliaSchmid, @jampani_varun and @g_kordo. Call for papers now open! All information on our website: https://t.co/y2jJrvpDAa
0
1
6