Pierre Harvey Richemond

5 papers · 2023–2024 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

ICML (4) ICLR (1)

Top co-authors

Bilal Piot (4) Yunhao Tang (4) Rémi Munos (3) Daniele Calandriello (3) Mark Rowland (3) Zhaohan Daniel Guo (3) Michal Valko (3) Bernardo Avila Pires (3) Charline Le Lan (2) Florian Strub (2)

Research topics

Machine Learning (5) Core Methods (3) Learning Types · Machine Learning (3) Optimization & Theory (3) Artificial Intelligence (2) Reinforcement Learning (2) Core AI (2) Methods (2) Deep Learning (1) Learning Types · Deep Learning (1)

Keywords

representation learning (3) self-predictive learning (2) ipo (2) semi-supervised learning (1) self-supervised learning (1) preference optimization (1) orthogonal projection (1) nash equilibrium (1) nearest neighbor (1) spectral decomposition (1) latent representation (1) prediction error (1) convex function (1) exponential moving average (1) preference model (1) predictor network (1) offline alignment (1) alignment (1) dpo (1) ipo-md (1)

Papers

Generalized Preference Optimization: A Unified Approach to Offline Alignment ICML 2024 Human Alignment of Large Language Models through Online Preference Optimisation ICML 2024 SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations ICLR 2023 The Edge of Orthogonality: A Simple View of What Makes BYOL Tick ICML 2023 Understanding Self-Predictive Learning for Reinforcement Learning ICML 2023