Yann Ollivier - RankMe

58 papers A* 11A 1Journal 39Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Likelihood-Based Reward Designs for General LLM Reasoning. CoRR Ariel Kwiatkowski, Natasha Butt, Ismail Labiad, Julia Kempe, Yann Ollivier
2026	J	`jnl`	Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability. CoRR Shobhita Sundaram, John Quan, Ariel Kwiatkowski, Kartik Ahuja, Yann Ollivier, Julia Kempe
2025	J	`jnl`	Soft Tokens, Hard Truths. CoRR Natasha Butt, Ariel Kwiatkowski, Ismail Labiad, Julia Kempe, Yann Ollivier
2025	J	`jnl`	Tackling the Zero-Shot Reinforcement Learning Loss Directly. CoRR Yann Ollivier
2025	J	`jnl`	Which Features are Best for Successor Features? CoRR Yann Ollivier
2024	A*	`conf`	Fast Imitation via Behavior Foundation Models. ICLR Matteo Pirotta, Andrea Tirinzoni, Ahmed Touati, Alessandro Lazaric, Yann Ollivier
2024	J	`jnl`	Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting. CoRR Edoardo Cetin, Ahmed Touati, Yann Ollivier
2024	A*	`conf`	Simple Ingredients for Offline Reinforcement Learning. ICML Edoardo Cetin, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric, Yann Ollivier, Ahmed Touati
2024	J	`jnl`	Simple Ingredients for Offline Reinforcement Learning. CoRR Edoardo Cetin, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric, Yann Ollivier, Ahmed Touati
2023	A*	`conf`	Does Zero-Shot Reinforcement Learning Exist? ICLR Ahmed Touati, Jérémy Rapin, Yann Ollivier
2022	J	`jnl`	Agnostic Physics-Driven Deep Learning. CoRR Benjamin Scellier, Siddhartha Mishra, Yoshua Bengio, Yann Ollivier
2022	J	`jnl`	Does Zero-Shot Reinforcement Learning Exist? CoRR Ahmed Touati, Jérémy Rapin, Yann Ollivier
2021	A*	`conf`	Learning One Representation to Optimize All Rewards. NeurIPS Ahmed Touati, Yann Ollivier
2021	J	`jnl`	Learning One Representation to Optimize All Rewards. CoRR Ahmed Touati, Yann Ollivier
2021	J	`jnl`	Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint. CoRR Léonard Blier, Corentin Tallec, Yann Ollivier
2021	J	`jnl`	Unbiased Methods for Multi-Goal Reinforcement Learning. CoRR Léonard Blier, Yann Ollivier
2020	J	`jnl`	Interpreting a Penalty as the Influence of a Bayesian Prior. CoRR Pierre Wolinski, Guillaume Charpiat, Yann Ollivier
2019	A*	`conf`	First-Order Adversarial Vulnerability of Neural Networks and Input Dimension. ICML Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz
2019	—	`conf`	Learning with Random Learning Rates. ECML/PKDD (2) Léonard Blier, Pierre Wolinski, Yann Ollivier
2019	A*	`conf`	Making Deep Q-learning methods robust to time discretization. ICML Corentin Tallec, Léonard Blier, Yann Ollivier
2019	J	`jnl`	Making Deep Q-learning methods robust to time discretization. CoRR Corentin Tallec, Léonard Blier, Yann Ollivier
2019	A*	`conf`	Separable value functions across time-scales. ICML Joshua Romoff, Peter Henderson, Ahmed Touati, Yann Ollivier, Joelle Pineau, Emma Brunskill
2019	J	`jnl`	Separating value functions across time-scales. CoRR Joshua Romoff, Peter Henderson, Ahmed Touati, Yann Ollivier, Emma Brunskill, Joelle Pineau
2019	A*	`conf`	White-box vs Black-box: Bayes Optimal Strategies for Membership Inference. ICML Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Yann Ollivier, Hervé Jégou
2019	J	`jnl`	White-box vs Black-box: Bayes Optimal Strategies for Membership Inference. CoRR Alexandre Sablayrolles, Matthijs Douze, Yann Ollivier, Cordelia Schmid, Hervé Jégou
2018	J	`jnl`	Adversarial Vulnerability of Neural Networks Increases With Input Dimension. CoRR Carl-Johann Simon-Gabriel, Yann Ollivier, Bernhard Schölkopf, Léon Bottou, David Lopez-Paz
2018	J	`jnl`	Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies. CoRR Yann Ollivier
2018	—	`conf`	Can recurrent neural networks warp time? ICLR (Poster) Corentin Tallec, Yann Ollivier
2018	J	`jnl`	Can recurrent neural networks warp time? CoRR Corentin Tallec, Yann Ollivier
2018	J	`jnl`	Do Deep Learning Models Have Too Many Parameters? An Information Theory Viewpoint. CoRR Léonard Blier, Yann Ollivier
2018	J	`jnl`	Learning with Random Learning Rates. CoRR Léonard Blier, Pierre Wolinski, Yann Ollivier
2018	A*	`conf`	Mixed batches and symmetric discriminators for GAN training. ICML Thomas Lucas, Corentin Tallec, Yann Ollivier, Jakob Verbeek
2018	J	`jnl`	Mixed batches and symmetric discriminators for GAN training. CoRR Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier
2018	A*	`conf`	The Description Length of Deep Learning models. NeurIPS Léonard Blier, Yann Ollivier
2018	—	`conf`	Unbiased Online Recurrent Optimization. ICLR (Poster) Corentin Tallec, Yann Ollivier
2017	J	`jnl`	Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles. J. Mach. Learn. Res. Yann Ollivier, Ludovic Arnold, Anne Auger, Nikolaus Hansen
2017	—	`conf`	Natural Langevin Dynamics for Neural Networks. GSI Gaétan Marceau-Caron, Yann Ollivier
2017	J	`jnl`	Natural Langevin Dynamics for Neural Networks. CoRR Gaétan Marceau-Caron, Yann Ollivier
2017	J	`jnl`	True Asymptotic Natural Gradient Optimization. CoRR Yann Ollivier
2017	J	`jnl`	Unbiased Online Recurrent Optimization. CoRR Corentin Tallec, Yann Ollivier
2017	J	`jnl`	Unbiasing Truncated Backpropagation Through Time. CoRR Corentin Tallec, Yann Ollivier
2016	J	`jnl`	Practical Riemannian Neural Networks. CoRR Gaétan Marceau-Caron, Yann Ollivier
2015	—	`conf`	Laplace's Rule of Succession in Information Geometry. GSI Yann Ollivier
2015	J	`jnl`	Laplace's rule of succession in information geometry. CoRR Yann Ollivier
2015	J	`jnl`	Speed learning on the fly. CoRR Pierre-Yves Massé, Yann Ollivier
2015	J	`jnl`	Training recurrent networks online without backtracking. CoRR Yann Ollivier, Guillaume Charpiat
2014	J	`jnl`	Auto-encoders: reconstruction versus compression. CoRR Yann Ollivier
2014	—	`book`	Optimal Transport - Theory and Applications. Optimal Transport Yann Ollivier, Herve Pajot, Cédric Villani
2013	—	`conf`	Information-Geometric Optimization: The Interest of Information Theory for Discrete and Continuous Optimization. GSI Yann Ollivier
2013	A	`conf`	Objective improvement in information-geometric optimization. FOGA Youhei Akimoto, Yann Ollivier
2013	J	`jnl`	Persistent Contextual Neural Networks for learning symbolic data sequences. CoRR Yann Ollivier
2013	J	`jnl`	Riemannian metrics for neural networks CoRR Yann Ollivier
2012	J	`jnl`	A Curved Brunn-Minkowski Inequality on the Discrete Hypercube, Or: What Is the Ricci Curvature of the Discrete Hypercube? SIAM J. Discret. Math. Yann Ollivier, Cédric Villani
2012	J	`jnl`	Layer-wise learning of deep generative models CoRR Ludovic Arnold, Yann Ollivier
2012	J	`jnl`	Objective Improvement in Information-Geometric Optimization CoRR Youhei Akimoto, Yann Ollivier
2007	A*	`conf`	Finding Related Pages Using Green Measures: An Illustration with Wikipedia. AAAI Yann Ollivier, Pierre Senellart
2007	J	`jnl`	Some Small Cancellation Properties of Random Groups. Int. J. Algebra Comput. Yann Ollivier
2003	J	`jnl`	Rate of convergence of crossover operators. Random Struct. Algorithms Yann Ollivier

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.