Lune

Profiles2022-2026

Riccardo De Santi

ETH AI Center

11Papers
0Last author
14Unique co-authors
6First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers11

  1. Landing with the Score: Riemannian Optimization through DenoisingAuthor 3 of 4ICLR 2026 · 7 citations
  2. Verifier-Constrained Flow Expansion for Discovery Beyond the DataAuthor 1 of 5ICLR 2026 · 6 citations
  3. A Unified Density Operator View of Flow Control and MergingAuthor 1 of 5ICML 2026 · 2 citations
  4. Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-TuningAuthor 1 of 6NeurIPS 2025 · 17 citations
  5. Provable Maximum Entropy Manifold Exploration via Diffusion ModelsAuthor 1 of 6ICML 2025
  6. Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient MethodsAuthor 1 of 3ICML 2024 · 14 citations
  7. Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement LearningAuthor 2 of 7ICLR 2024 · 6 citations
  8. Geometric Active Exploration in Markov Decision Processes: the Benefit of AbstractionAuthor 1 of 5ICML 2024 · 5 citations
  9. Provably Efficient Causal Model-Based Reinforcement Learning for Systematic GeneralizationAuthor 2 of 6AAAI 2023 · 17 citations
  10. The Importance of Non-Markovianity in Maximum State Entropy ExplorationAuthor 2 of 3ICML 2022 · 45 citations
  11. Challenging Common Assumptions in Convex Reinforcement LearningAuthor 2 of 4NeurIPS 2022 · 31 citations
Dusk over the sea between two cliffs drawn in fine vertical lines