chriswolfvision.bsky.social
Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. https://chriswolfvision.github.io/www/
856 posts
5,831 followers
701 following
Regular Contributor
Active Commenter
comment in response to
post
Perhaps all of them!
comment in response to
post
Thanks, will change (and delete)
comment in response to
post
This only works if you you used it in "I mean" as a phrase in itself, which then introduces a completely independent sentence, indeed.
However, if you say "I meant X" to provide more specifics to something previously discussed, then I am hard-pressed to find an equally short expression.
comment in response to
post
Indeed! But too long to use in an English text. So "observation" it is 😆
comment in response to
post
DUNE 🏜️ - multi-teacher distillation extended to heterogeneous teachers: DiNOv2, Multi-HMR and MASt3R - #CVPR2025
Paper: arxiv.org/abs/2503.14405
Project page: europe.naverlabs.com/dune
comment in response to
post
I just deleted my FB and instagram accounts 2 months ago, which I hadn't used anyway 😉
comment in response to
post
Indeed. How can there even be a debate on cheese, come on 😁
comment in response to
post
I have a very open mind but I considered blocking for this 😂
comment in response to
post
😂
comment in response to
post
Of course it was!
(In terms of desserts, the main competition is, of course, Austria, and it's better 😁)
comment in response to
post
To be honest, my ❤️ above only applied to Madeleines and not to Meringues 😀
comment in response to
post
Thanks David and all the other organizers for this really great event, we had a blast!
Yes, please do it again next year 😀
comment in response to
post
I recommend the lab Diane comes from 😁
comment in response to
post
TIL that papillon not only means butterfly 😱
comment in response to
post
Wow!
comment in response to
post
A prompt, which produces itself as an output, up to a linear factor (repetition)?
comment in response to
post
I am glad you compensate this with world class research, because the cheap gin alone would not help to attract students 😆
comment in response to
post
Where is @davidpicard.bsky.social ?
comment in response to
post
Yes, I agree.
comment in response to
post
I think bibliometrics has its faults, but it gives some direction. Having bibliometrics is better than not having any. We know the appreciations of all the famous works (eg. Sift, HoG before, transformers after), but lots of other things are more difficult to have an opinion on w/o bibliometrics.
comment in response to
post
I was doing my PhD when scholar was introduced. It dramatically changed the perception of who was impactful at several departments, as people considered being impactful (eg bc they wrote some books) were found out to not much be cited.
comment in response to
post
Real scientific progress is always free ... for the authors but not for the authors who have put sweat into it 😀
comment in response to
post
On "bullshitting" LLMs in the chain of thought experiments:
comment in response to
post
comment in response to
post
Insights into the jailbraking mechanism: the model internally recognizes that is asked to provide help to make a bomb, but it is in the middle of a sentence. So the refusal mechanism is deferred until the current sentence is finished, because being dramatically correct is more important.
comment in response to
post
Insights into the jailbraking mechanism: the model internally recognizes that is asked to provide help to make a bomb, but it is in the middle of a sentence. So the refusal mechanism is deferred until the current sentence is finished, because being dramatically correct is more important.
comment in response to
post
I just unsubscribed last week 🙁