Le Hellard, Théotime

3 publications

ICLR 2026 Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning Franki NGUIMATSIA Tiofack, Théotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier

ICML 2025 HiRemate: Hierarchical Approach for Efficient Re-Materialization of Neural Networks Julia Gusak, Xunyi Zhao, Théotime Le Hellard, Zhe Li, Lionel Eyraud-Dubois, Olivier Beaumont

ICML 2023 Rockmate: An Efficient, Fast, Automatic and Generic Tool for Re-Materialization in PyTorch Xunyi Zhao, Théotime Le Hellard, Lionel Eyraud-Dubois, Julia Gusak, Olivier Beaumont