Victor Letzelter @ ICML 2026 (@VLetzelter) header
Victor Letzelter @ ICML 2026 (@VLetzelter) profile picture

Research Scientist @ Mistral

Paris, France
Joined September 2021
Victor Letzelter @ ICML 2026 retweeted
Voxtral Small Transcribe 3 is state-of-the-art in multilingual transcription, diarization and context-biasing. It detects when someone has finished speaking so agents can respond without delay.
11
14
4
196
21,304
Victor Letzelter @ ICML 2026 retweeted
1/n Our paper REPA-G is accepted at #NeurIPS2026! 🎉 I'll present it at the NeurIPS Paris site 🇫🇷. We introduce test-time conditioning of REPA-style diffusion models with visual features, with no extra training.
3
25
119
5,761
Victor Letzelter @ ICML 2026 retweeted
Introducing Mistral OCR 4. It creates structure with bounding boxes, block classification, and inline confidence scores in 170 languages. 🧵👇
207
475
161
5,509
1,324,535
Victor Letzelter @ ICML 2026 retweeted
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
🚨 Happening NOW! 🎓 Our PhD student Victor Letzelter @VLetzelter is currently defending his thesis at Telecom Paris! Good luck, Victor! 👏🚀 #PhDDefense #TelecomParis
1
2
19
3,073
Victor Letzelter @ ICML 2026 retweeted
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. 📄 arxiv.org/pdf/2602.03753 💻 github.com/valeoai/REPA-G 🧵👇
1
19
1
90
5,342
Victor Letzelter @ ICML 2026 retweeted
🚗 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]
6
49
11
174
30,226
Victor Letzelter @ ICML 2026 retweeted
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.
2
1
9
592
Victor Letzelter @ ICML 2026 retweeted
🌟 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: valeoai.github.io/interns/ RT to spread the word! 🙌
8
3
17
7,890
Victor Letzelter @ ICML 2026 retweeted
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
1
2
1
10
945
Victor Letzelter @ ICML 2026 retweeted
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: arxiv.org/abs/2408.02514 Code: github.com/SonyCSLParis/Stem…
3
14
2
49
6,660
Victor Letzelter @ ICML 2026 retweeted
.@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]
3
6
589
Victor Letzelter @ ICML 2026 retweeted
Interested in unsupervised domain adaptation for LiDAR data ? Then, I am happy to see you at the spotlight presentation of our paper “SALUDA” this afternoon at 15:00 or at the poster session @3DVconf. Paper: arxiv.org/abs/2304.03251 Code: github.com/valeoai/SALUDA
1
6
2
14
3,504