publications
2025
- arXivMimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language ModelsPreprint, 2025
- ICMLDiffuse Everything: Multimodal Diffusion Models on Arbitrary State SpacesInternational Conference on Machine Learning (ICML), 2025
- ICMLLearning to Stop: Deep Learning for Mean Field Optimal StoppingInternational Conference on Machine Learning (ICML), 2025
- arXivFast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order AlgorithmsICLR FPI Workshop, 2025Long version under review
2024
- arXiv
- arXivCompetitive Reinforcement Learning when Minimax Theorem Does Not Hold: Multi-Objective Markov Games, Multi-Calibration, and BeyondPreprint, 2024
- arXiv
- ESAIM