Sorbonne university
Joined May 2009
- Tweets 146
- Following 107
- Followers 520
- Likes 74
28 Photos and videos
Thanks all for coming to Paris @ICCVConference and making it such an amazing event.
As warned, we brought the whole @valeoai family, interns and seniors alike, and it was a blast!
We are so happy to share good papers, discussions and laughs. What an amazing community #ICCV2023
From interns to senior researchers, the @valeoai team will participate in mass at @ICCVConference and will be looking forward to welcoming you and talking about the exciting progress and ideas in the field.
Check our #ICCV2023 works and come meet us 👇valeoai.github.io/blog/2023/…
7
29
6,186
Matthieu Cord retweeted
7 Oct 2023
At #ICCV2023, presenting our work ep-ALM with @MustafaShukor1 and @quobbe. Check out the website at mshukor.github.io/eP-ALM.git…
2
29
2,066
Matthieu Cord retweeted
3 Oct 2023
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks. 👉A unified foundation model that can process images, videos and audios-language tasks, trained with academic compute budget, on public datasets. Project: unival-model.github.io/ Workshop: Monday in MMFM
1
4
7
833
Matthieu Cord retweeted
3 Oct 2023
The team is active at #ICCV2023, come and say Hi to the Chordettes! They are talking about LLMs, multimodality, foundation models, diffusion models and more! Check their papers: 👇
1
7
30
2,516
Matthieu Cord retweeted
30 Jun 2023
Félicitations à @HugoTouvron qui a obtenu le prix de thèse Signal, Image et Vision 2023 décerné par le GdR ISIS !
"Architectures and Training for visual understanding"
et supervisée par @quobbe et @hjegou from @meta
tel.archives-ouvertes.fr/tel…
@Sorbonne_Univ_ @ISIR_labo
1
8
55
3,872
We're happy to announce the #ICCV2023 BRAVO Workshop: roBust and Reliability of Autonomous Vehicles in the Open-world. We welcome full papers and extended abstracts on robustness, generalization, transparency, and verification of computer vision models valeoai.github.io/bravo/
1
10
14
4,301
Matthieu Cord retweeted
31 Mar 2023
Congratulations to Corentin! Bravo!
30 Mar 2023
Tomorrow 3p.m., @cdancette will defend his thesis entitled "Shortcut Learning in Visual Question Answering"
The defense will take place @Sorbonne_Univ_ in RC27, bâtiment Atrium.
The defense will also be broadcasted: youtube.com/watch?v=2ItDfiMK…
Stay tuned!
1
10
1,988
Matthieu Cord retweeted
31 Mar 2023
PhD defense of Corentin Dancette @cdancette at Sorbonne University, Paris, on Shortcut learning in VQA. Committee: @quobbe @thomenicolas1 @DamienTeney @marcus_rohrbach Elisa Fromont and yours, truly.
2
18
1,860
Matthieu Cord retweeted
31 Mar 2023
Same. My biggest fear is not the Terminator apocalypse, but more what could happen if a large number of people ask an LLM "Sum up the candidates ideas and tell me which one is the most aligned with me" during the next elections.
Not voting, because yes/no is too restrictive.
1
1
1
243
Matthieu Cord retweeted
24 Feb 2023
Today we release LLaMA, 4 foundation models ranging from 7B to 65B parameters.
LLaMA-13B outperforms OPT and GPT-3 175B on most benchmarks. LLaMA-65B is competitive with Chinchilla 70B and PaLM 540B.
The weights for all models are open and available at research.facebook.com/public…
1/n
150
1,347
6,511
3,227,037
Matthieu Cord retweeted
1 Dec 2022
Our researchers are attending @NeurIPSConf #NeurIPS2023
Do not hesitate to reach them and discuss with them.
Review once again our papers in the following thread ⬇️⬇️⬇️
13 Oct 2022
Have a look at our 7 @NeurIPSConf papers!
Congrats to all authors đź‘Źđź‘Źđź‘Ź
(7/7) "SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance"
by E. Yvinec, A. Dapogny, @quobbe, K. Bailly
arxiv.org/abs/2207.04089
Collab w/ @DatakaLab
2
4
Matthieu Cord retweeted
24 Oct 2022
First #ECCV2022 evening with @quobbe in a nice restaurant in town. It's been a long time since the last time and we had a lot of things to talk about. There are few things as enjoyable as meeting your PhD supervisor at a conference long after you defended. 10/10, would recommend.
2
1
19
DiffEdit: Diffusion-based semantic image editing with mask guidance
abs: arxiv.org/abs/2210.11427
3
46
206
30 Sep 2022
1
30 Sep 2022
Cookbook for Vision Transformers deeplearning.ai/the-batch/is…
Good insight about our DeiT III in the @AndrewYNg’s news letter
I will present it with Hugo at ECCV 2022!
1
1
3
Matthieu Cord retweeted
29 Sep 2022
I’d like to address the serious matter of some newcomers to AI experiencing imposter syndrome, where someone wonders if they’re a fraud or really belong in the AI community. Lets build a community that encourages and welcomes everyone. deeplearning.ai/the-batch/is…
31
116
779
Matthieu Cord retweeted
21 Sep 2022
Our paper "LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation" made it to #CoRL2022 🥳
w/ F. Bartoccioni, A. Bursuc (@abursuc), P. PĂ©rez, Matthieu Cord (@quobbe) & K. Alahari (@inthebrownbag)
arxiv: arxiv.org/abs/2206.13294
code: github.com/valeoai/LaRa
1
8
31
Matthieu Cord retweeted
29 Sep 2022
Congratulations to @HugoTouvron who brightly defended his PhD thesis today! đź‘Źđź‘Źđź‘Ź
Thank you for the very interesting presentation of your work! Good luck for the future!
3
4
30
Matthieu Cord retweeted
9 Sep 2022
One of my all-time favorite illusions: The spinning dancer
If you look at the dancer on the left and the one in the middle, the one in the middle spins clockwise.
If you look at the dancer on the *right* and the one in the middle, the one in the middle spins counterclockwise.
60
994
4,862
Matthieu Cord retweeted
22 Jul 2022
Happy to share that our work has been accepted to ECCV 2022!
"STEEX: Steering Counterfactual Explanations with Semantics"🚙🔎
w/ P. Jacob, H. Ben-Younes (@LaBegne), @Mickael_Chen, P. PĂ©rez, and M. Cord (@quobbe).
paper: arxiv.org/abs/2111.09094
code: github.com/valeoai/steex
2
7
13