← authors · overview

• Optimizing the Latent Space of Generative Networks
  2017 · 203 citations
• Modeling Others using Oneself in Multi-Agent Reinforcement Learning
  2018 · 68 citations
• Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning
  2018 · 15 citations
• CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory
  2022 · 11 citations
• Fast Adaptation via Policy-Dynamics Value Functions
  2020 · 9 citations
• DiLoCo: Distributed Low-Communication Training of Language Models
  2023 · 7 citations
• Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
  2025
• Empirically Verifying Hypotheses Using Reinforcement Learning
  2020
• Asynchronous Local-SGD Training for Language Modeling
  2024
• Deliberation in Latent Space via Differentiable Cache Augmentation
  2024