Criteo AI Lab
@CriteoAILab
Followers
2K
Following
656
Media
331
Statuses
1K
Connecting shoppers to products and brands via creation, development and deployment of AI models that are transparent & interpretable. https://t.co/WbRVAHD4lF
Paris, France
Joined August 2016
🔴 A new Research Card is out! 🧪 Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search 🔎 A rule for choosing when to sell/buy an asset when facing a sequence of prices. #AdTech Read our article to discover more! 👇 https://t.co/U2VseBWSCC
medium.com
Tech stories from the Criteo R&D team
0
2
4
At @criteo , we believe that #MCP will be key to empowering our clients and giving them the control to create and manage advertising campaigns in a new way. Check our latest tech article about "Lessons From Engineering Our MCP Server" 👇 #adtech
https://t.co/DEUmsU4qaw
medium.com
Authors: Jean-Baptiste Muscat-Dupuis & Justine Jaffe
0
1
4
Poser presentation - Tuesday 23 Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation by Alessandro B. Melchiorre, Elena Epure, Shahed Masoudian, Gustavo Escobedo, Anna Hausberger, Manuel Moussallam, Markus Schedl https://t.co/vh0L2JyVt4
arxiv.org
Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs) show promise in...
0
0
1
DaQuaMRec Workshop - Monday 22 📌 Room D7 Org: Alessandro Melchiorre
1
0
1
Non-Linear Counterfactual Aggregate Optimization by @BenjaminHe12201 and @OtmaneSakhi
https://t.co/wiQQ57gCgQ
arxiv.org
We consider the problem of directly optimizing a non-linear function of an outcome, where this outcome itself is the sum of many small contributions. The non-linearity of the function means that...
1
1
2
📜Two poster presentations Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation by @imad_aouali and @OtmaneSakhi
https://t.co/xy3bGpU5W9
arxiv.org
Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved...
1
0
1
CONSEQUENCES '25 Workshop - Monday 22 📌 Room D3 Org: @flavianv 🗣️Spotlight Talk: Offline Contextual Bandit with Counterfactual Sample Identification by Alexandre Gilotte, @OtmaneSakhi , @imad_aouali and @BenjaminHe12201
https://t.co/cxgR1mmO30
arxiv.org
In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it...
1
2
3
📢For all of you attending #RecSys2025 next week, don't miss all our contributions 👀 Check the following thread to know more about everything we will share at @ACMRecSys 🧵👇
1
0
1
🔍 Zebra: In-Context Generative Pretraining for Solving Parametric PDEs 🗓️ Thu 17 Jul 11 a.m. PDT — 1:30 p.m. PDT 📍West Exhibition Hall B2-B3 # W-106 ✍ Louis Serrano · Armand Kassaï Koupaï · Thomas Wang · Pierre ERBACHER · Patrick Gallinari 🔗 https://t.co/uHjqI7L2hc
0
0
0
🔍 The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback 🗓️ Thu 17 Jul 11AM PDT 📍East Exhibition Hall A-B # E-1902 ✍ Côme Fiegel · Pierre Menard · Tadashi Kozuno · Michal Valko · Vianney Perchet 🔗 https://t.co/hLpOOzbBu9
1
0
0
🔍 Improving Consistency Models with Generator-Augmented Flows 🌟 Spotlight Poster 🗓️ Wed 16 Jul 11 AM PDT 📍East Exhibition Hall A-B # E-3200 ✍ Thibaut Issenhuth, Sangchul Lee, Ludovic DOS SANTOS, Jean-Yves Franceschi, Chansoo Kim, Alain Rakotomamonjy 🔗 https://t.co/6oKeVmPwmb
1
1
1
🔍 Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search 🗓️ Tue 15 Jul 11 a.m. PDT — 1:30 p.m. PDT 📍West Exhibition Hall B2-B3 hashtag#W-1007 ✍ Ziyad Benomar · Lorenzo Croissant · Vianney Perchet · Spyros Angelopoulos 🔗 https://t.co/8Ur2ZRleB2
1
0
0
The 2025 edition of @icmlconf is happening this week and there will be some Criteos around 🧡 Check our contributions and don't hesitate to engage with them to know more 👀 Papers in the thread 🧵 👇
1
1
1
🔴 A new tech meetup in our BCN office is coming up! Don't miss 🎤 @albertlumbreras' talk: "The #agentic paradigm: planning the future for machines that plan" - A new reality where #AI evolves from predictive models to autonomous agents. 🔗 RSVP here! https://t.co/IeAwFCU78K
0
2
2
🔴 A new Research Card is out! 🔴 Check it out to learn more about improving consistency models with generator-augmented flows. This could mean delivering more personalized ads in real-time - boosting engagement and cutting infrastructure costs 🤯 https://t.co/bsaXJ5ZAUu
medium.com
Tech stories from the Criteo R&D team
0
1
0
We sponsored #ALT2025 this year and had a strong presence at the conference, contributing and presenting research that showcased our commitment to innovation. One of our papers received an Outstanding Paper Award 🎉 Read the full recap to know more. https://t.co/xHn88cVm90
medium.com
Tech stories from the Criteo R&D team
0
0
4
🔴 New research card is out! 🔴 This Research Card introduces a novel Inverse Graphics Autoencoder (IG-AE) that creates a 3D-aware latent space compatible with Neural Radiance Fields (NeRFs) 🤯 Read more 👇 https://t.co/7GECKg1vq9
medium.com
Tech stories from the Criteo R&D team
0
2
1
🔴 New research card is out! 🔴 This Research Card introduces a novel differentially private model using gradient flows defined on an optimal transport metric. 🤯 Read more 👇 https://t.co/LgfZVrHTov
medium.com
Tech stories from the Criteo R&D team
0
2
1