's Avatar

@andreugirbau

Current: Researcher @ Denso IT lab (Tokyo). Prev: PhD @UPC, Postdoc @ NII

911
Followers
544
Following
38
Posts
19.11.2024
Joined
Posts Following

Latest posts by @andreugirbau

Post image

Space robotics is super cool. I love learning from different research and human perspectives.

01.12.2025 04:51 ๐Ÿ‘ 2 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Me: Hey, this research idea seems simple enough and pretty interesting. I'll allocate a week and try it real quick.

3 days later

Me: Huh, so that's how kubernetes work...

03.10.2025 07:04 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Anyone knows where are the demos?

@cvprconference.bsky.social

13.06.2025 16:49 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

They say the second is the first loser...

Happy to announce we got second best paper in the Event Vision workshop @cvprconference.bsky.social for the paper Probabilistic Online Event Downsampling!

www.arxiv.org/pdf/2506.02547

13.06.2025 11:23 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Post image

At #CVPR2025!
So far:
+ Breakfast was super good!
- While tutorials and workshops said "from 8" in their sites, it seems that the official time has been delayed to "from 9" without any update or contact from the organizers.

So yep, here we are, the ones who woke up early and ate fast, waiting.

11.06.2025 13:24 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

Deadline mode

10.03.2025 08:00 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

CVPR is getting savage, all my reviewer batch rejected :0

28.02.2025 03:33 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Wow, that's something I didn't know I needed

04.02.2025 23:17 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Reading some reviews and the corresponding rebuttals is like looking at a conversation between two chat gpts...

04.02.2025 02:00 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image Post image

Great talk by @abursuc.bsky.social on foundational models, fine tunnings and the lots of difficulties on autonomous driving #MMM2025

10.01.2025 02:00 ๐Ÿ‘ 11 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

One of the best parts of any conference

#MMM2025

09.01.2025 15:09 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

First keynote by Nancy Chen begins! #MMM2025

08.01.2025 01:01 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image Post image Post image

Ready to go! #MMM2025

07.01.2025 23:48 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image Post image

Getting ready! #MMM2025

07.01.2025 05:06 ๐Ÿ‘ 4 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

Omw to finish the preparations for #MMM2025 in Nara!

My first experience in an international conference organizing committee, it will be a blast!

07.01.2025 00:16 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Nono, just random thoughts

24.12.2024 08:06 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

I'm always conflicted with the science (?) of AI research.

Sometimes I read "we discovered that doing A is useful to solving this task", but in my mind is "we made A, and forced it to solve this task by tweaking this and that".

Am I missing something?

24.12.2024 05:49 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 2 ๐Ÿ“Œ 0

Got the same in descending order ๐Ÿค™๐Ÿค™

18.12.2024 00:05 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

๐Ÿคž๐Ÿคž

15.12.2024 06:57 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

Or 8 ๐Ÿซ 

15.12.2024 05:54 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

4 papers assigned for #CVPR25 and all super well aligned with my research. Good job ACs! @cvprconference.bsky.social

15.12.2024 04:22 ๐Ÿ‘ 3 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

Within 1 sigma to the right side, still way to go

13.12.2024 15:05 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

I made a meme

12.12.2024 10:14 ๐Ÿ‘ 3 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

When working with docker + live cameras is latency super noticeable?

09.12.2024 10:07 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
a man in a suit and tie is holding a newspaper in his hand ALT: a man in a suit and tie is holding a newspaper in his hand

Registration for #DLBCN 2024 is now open for the general public. Get your ticket today !

sites.google.com/view/dlbcn20...

09.12.2024 07:08 ๐Ÿ‘ 2 ๐Ÿ” 2 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
Generating Worlds Today we're sharing our first step towards spatial intelligence: an AI system that generates 3D worlds from a single image.

Incredible work being done by @drfeifei.bsky.social et al. on 3D world generation.

Also super cool demos!

www.worldlabs.ai/blog

04.12.2024 04:22 ๐Ÿ‘ 3 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

@violetilla.bsky.social ๐Ÿ‘‹๐Ÿ‘‹

27.11.2024 13:54 ๐Ÿ‘ 2 ๐Ÿ” 0 ๐Ÿ’ฌ 2 ๐Ÿ“Œ 0
Post image

Looking at ICLR submissions with the lowest score - What a work of art! ๐Ÿงต

25.11.2024 17:52 ๐Ÿ‘ 171 ๐Ÿ” 19 ๐Ÿ’ฌ 5 ๐Ÿ“Œ 9

It's a must, his posts are gold

26.11.2024 10:11 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image Post image Post image Post image

My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.

fleuret.org/dlc/

And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)

fleuret.org/lbdl/

26.11.2024 06:15 ๐Ÿ‘ 1252 ๐Ÿ” 248 ๐Ÿ’ฌ 46 ๐Ÿ“Œ 17