233 citations · 531 across the 34 of their papers we have counts for
35 papers
Off-Policy Learning to Reason Works Because It Is More Pessimistic Than You Think
Otmane Sakhi, Aleksei Arzhantsev, Imad Aouali +1
Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates…
SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion
Antoine Schnepf, Karim Kassab, Flavian Vasile +1
The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fund…
RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
Imad Aouali, Flavian Vasile, Otmane Sakhi +2
LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduc…
RoiRL: Efficient, Self-Supervised Reasoning with Offline Iterative Reinforcement Learning
Aleksei Arzhantsev, Otmane Sakhi, Flavian Vasile
Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) r…
Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi +5
Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice t…
Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides red…
Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory…
3DGEN: A GAN-based approach for generating novel 3D models from image data
Antoine Schnepf, Flavian Vasile, Ugo Tanielian
The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields. However, a less explored area is the one of 3D model ge…
AdBooster: Personalized Ad Creative Generation using Stable Diffusion Outpainting
Veronika Shilova, Ludovic Dos Santos, Flavian Vasile +2
In digital advertising, the selection of the optimal item (recommendation) and its best creative presentation (creative optimization) have traditionally been considered separate di…
Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation
Imad Aouali, Amine Benhalloum, Martin Bompaire +5
Both in academic and industry-based research, online evaluation methods are seen as the golden standard for interactive applications like recommendation systems. Naturally, the rea…
Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation
Imad Aouali, Achraf Ait Sidi Hammou, Otmane Sakhi +2
We introduce Probabilistic Rank and Reward (PRR), a scalable probabilistic model for personalized slate recommendation. Our approach allows off-policy estimation of the reward in t…
Welfare-Optimized Recommender Systems
Benjamin Heymann, Flavian Vasile, David Rohde
We present a recommender system based on the Random Utility Model. Online shoppers are modeled as rational decision makers with limited information, and the recommendation task is…
What Users Want? WARHOL: A Generative Model for Recommendation
Jules Samaran, Ugo Tanielian, Romain Beaumont +1
Current recommendation approaches help online merchants predict, for each visiting user, which subset of their existing products is the most relevant. However, besides being intere…
Combining Reward and Rank Signals for Slate Recommendation
Imad Aouali, Sergey Ivanov, Mike Gartrell +4
We consider the problem of slate recommendation, where the recommender system presents a user with a collection or slate composed of K recommended items at once. If the user finds…
Improving Offline Contextual Bandits with Distributional Robustness
Otmane Sakhi, Louis Faury, Flavian Vasile
This paper extends the Distributionally Robust Optimization (DRO) approach for offline contextual bandits. Specifically, we leverage this framework to introduce a convex reformulat…
From Clicks to Conversions: Recommendation for long-term reward
Philomène Chagniot, Flavian Vasile, David Rohde
Recommender systems are often optimised for short-term reward: a recommendation is considered successful if a reward (e.g. a click) can be observed immediately after the recommenda…
BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals
Otmane Sakhi, Stephen Bonner, David Rohde +1
A common task for recommender systems is to build a pro le of the interests of a user from items in their browsing history and later to recommend items to the user from the same ca…
Reconsidering Analytical Variational Bounds for Output Layers of Deep Networks
Otmane Sakhi, Stephen Bonner, David Rohde +1
The combination of the re-parameterization trick with the use of variational auto-encoders has caused a sensation in Bayesian deep learning, allowing the training of realistic gene…
Learning from Bandit Feedback: An Overview of the State-of-the-art
Olivier Jeunen, Dmytro Mykhaylov, David Rohde +3
In machine learning we often try to optimise a decision rule that would have worked well over a historical dataset; this is the so called empirical risk minimisation principle. In…
Relaxed Softmax for learning from Positive and Unlabeled data
Ugo Tanielian, Flavian Vasile
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss…
Recommendation System-based Upper Confidence Bound for Online Advertising
Nhan Nguyen-Thanh, Dana Marinca, Kinda Khawam +5
In this paper, the method UCB-RS, which resorts to recommendation system (RS) for enhancing the upper-confidence bound algorithm UCB, is presented. The proposed method is used for…
On the Value of Bandit Feedback for Offline Recommender System Evaluation
Olivier Jeunen, David Rohde, Flavian Vasile
In academic literature, recommender systems are often evaluated on the task of next-item prediction. The procedure aims to give an answer to the question: "Given the natural sequen…
Distributionally Robust Counterfactual Risk Minimization
Louis Faury, Ugo Tanielian, Flavian Vasile +2
This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literat…
Causal Embeddings for Recommendation: An Extended Abstract
Stephen Bonner, Flavian Vasile
Recommendations are commonly used to modify user's natural behavior, for example, increasing product sales or the time spent on a website. This results in a gap between the ultimat…