research Sample-Efficient Reinforcement Learning under Sparse Dynamics 2026 · Exploiting sparse dynamics for sample-efficient model-based reinforcement learning. A Multi-objective Approach to Safe Reinforcement Learning for Smart Grids 2025 · Balancing energy costs and safety with multi-objective reinforcement learning. "Approximately Universally Intelligent" — How AIXI can Inspire Practical AI Algorithms 2025 · The promises and limitations of universal artificial intelligence and practical AIXI approximations. How Transformers Speak: An Interacting Multi-Particle System Perspective 2024 · Understanding transformer token dynamics through interacting particle systems. Game-Theoretic Multi-Agent Reinforcement Learning 2024 · Game theory, opponent-learning awareness, and cooperation in multi-agent reinforcement learning. Factory Manipulation with Cooperative Multi-Agent Reinforcement Learning 2024 · Training robot arms to cooperate in simulated factory manipulation. Flood Forecasting with Graph Neural Networks 2023 · Investigating whether river network topology improves neural flood forecasts. Attraction-Repulsion Dynamics versus Homophily in GNNs 2023 · Exploring attraction, repulsion, and graph homophily in the Gradient Flow Framework. Noise Schedules for Diffusion Probabilistic Models 2022 · Comparing noise schedules for diffusion-based image generation. Deep Active Learning with Artificial Neural Networks for Automatic Detection of Mercury’s Bow Shock and Magnetopause Crossing Signatures in NASA’s MESSENGER Magnetometer Observations 2021 · Active learning for detecting Mercury's bow shock and magnetopause crossings. Finding Single-Source Shortest Paths on Planar Graphs with Nonnegative Edge Weights in Linear Time 2020 · A linear-time algorithm for shortest paths in planar graphs.