Bogdan Mazoure

14 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7)

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🏃 Academic Marathon (7) 🧬 Topic Evolution 🗃️ Keyword Collector (63) 💎 Century Club (14) 🔥 Unstoppable (8) 📈 Trend Setter 🚀 Conference Pioneer

Conferences

ICLR (4) NIPS (3) AISTATS (2) CORL (2) AAAI (1) CVPR (1) EMNLP (1)

Top co-authors

R Devon Hjelm (5) Thang Doan (4) Harsh Agrawal (3) Andrew Szot (3) Audrey Durand (2) Zsolt Kira (2) Alexander Toshev (2) Ofir Nachum (2) Devon Hjelm (2) Guillaume Rabusseau (2)

Keywords

reinforcement learning (3) generative adversarial network (2) contrastive learning (2) continual learning (2) multimodal large language model (2) offline reinforcement learning (2) catastrophic forgetting (1) style transfer (1) neural tangent kernel (1) principal component analysis (1) value function (1) curriculum learning (1) visual question answering (1) self-supervised learning (1) image generation (1) mutual information (1) social network analysis (1) embodied ai (1) adversarial training (1) sample efficiency (1)

Papers

From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons CVPR 2025 On the Modeling Capabilities of Large Language Models for Sequential Decision Making ICLR 2025 Large Language Models as Generalizable Policies for Embodied Tasks ICLR 2024 Grounding Multimodal Large Language Models in Actions NIPS 2024 Contrastive Value Learning: Implicit Models for Simple Offline RL CORL 2023 Learning About Progress From Experts ICLR 2023 Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL ICLR 2022 Improving Zero-Shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions NIPS 2022 A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix AISTATS 2021 Deep Reinforcement and InfoMax Learning NIPS 2020 Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning AISTATS 2020 On-Line Adaptative Curriculum Learning for GANs AAAI 2019 Leveraging exploration in off-policy algorithms via normalizing flows CORL 2019 EmojiGAN: learning emojis distributions with a generative model EMNLP 2018