Congrats to our @VLetzelter for earning his well deserved PhD with his works on "Multiple Choice Learning from Ambiguous Signals".
Victor is a resourceful, curious and kind researcher. Good luck for next!
Fruit of an excellent collaboration between @telecomparis & @valeoai
Congrats to our @VLetzelter for earning his well deserved PhD with his works on "Multiple Choice Learning from Ambiguous Signals".
Victor is a resourceful, curious and kind researcher. Good luck for next!
Fruit of an excellent collaboration between @telecomparis & @valeoai
1/ 📢 New preprint: Test-Time Conditioning with Representation-Aligned Visual Features
Introducing REPA-G — a framework for controllable image generation at inference time using aligned visual features.
📄 https://t.co/bVlx3GqON5
💻 https://t.co/zIGVH25p3V
🧵👇
Interested in time series forecasting and data uncertainty quantification?
Check out our latest paper with @VLetzelter at @icmlconf !
Paper: https://t.co/4YOHCe7YZZ
Code: https://t.co/phdIpgEFQG
Poster #2211 , Tue 15 Jul 11 a.m. PDT East
#timeseries#quantization#uncertainty
🚗 Ever wondered if an AI model could learn to drive just by watching YouTube? 🎥👀
We trained a 1.2B parameter model on 1,800+ hours of raw driving videos.
No labels. No maps. Just pure observation.
And it works! 🤯
🧵👇 [1/10]
Inferring 3D human poses from video is highly ill-posed because of depth ambiguity.
Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.
🌟 Calling all MSc students passionate about computer vision and ML!
We’re offering research internships about diffusion models, multi-modal transformers, continual learning, & more. 4 exciting openings await!
🔗 Learn more: https://t.co/HNVWpI5QJ3
RT to spread the word! 🙌
Check out the paper!
Arxiv: https://t.co/caolTDEqn2
Project page: https://t.co/gb7wSBiNmH
GitHub: https://t.co/JoqsHUZem5
A joint work with David Perera, Théo Mariotte, Adrien Cortes, @Mickael_Chen , Slim Essid and Gaël Richard at @valeoai and Télécom Paris.
Working on ill-posed machine learning tasks, interested in multi-heads neural networks and data #uncertainty quantification ?
Sharing here our latest research, which will be presented at @NeurIPSConf in December.
Key insights:
* Annealing enhances exploration compared to greedy convergence.
* Inspired by statistical physics and information theory, we describe the training trajectory.
* Experiments on synthetic datasets, UCI benchmarks, and speech separation show highly promising results.
You have an already trained sem. segmentation model ?
You want to apply it to data with a domain shift ?
You are afraid of degradation during the adaptation ?
Then you might want to check out our work TTYD at @eccvconf 2024 in Milan.
👉 Poster # 73: Tuesday, 16:30
#ECCV2024
Glad to announce that Stem-JEPA has been accepted to @ISMIRConf !
In this work, we tackle the task of musical stem compatibility estimation (what “fits” together) as a representation learning problem. (1/7)
Paper: https://t.co/Gx0NenVZes
Code: https://t.co/qpwzIdVN5C
.@VLetzelter will be at #ICML2024 to present his work on leveraging the geometric properties of the Winner-takes-all learners for conditional density estimation & uncertainty prediction, w/o modifying its original training scheme.
Find a tl;dr below & come say hi at the posters
Interested in ill-posed learning tasks, uncertainty prediction, conditional density estimation or multi-head deep neural networks ?
In our new paper, accepted at #ICML24, we tackle these challenges by exploring the Winner-Takes-All (WTA) training scheme.
[1/n]
The attached figure illustrates the predictions (shaded blue points) made by WTA-based models compared to other baselines, for the task of estimating conditional distributions on a synthetic datasets (represented by green points).
[4/n]