-
🔥🔥🔥 [May 19, 2025] We released OpenRBench, a benchmark for evaluating massive multimodal understanding and reasoning in open space. Code, dataset, and leaderboard are available at: https://open-space-reasoning.github.io
-
🔥🔥🔥 [May 07, 2025] We released RLBenchNet, a systematic benchmarking suite for evaluating neural network architectures in reinforcement learning. Code is available at: https://github.com/SafeRL-Lab/BenchNetRL
-
🔭 We focus on the theory and practice of machine learning, with applications to robotics and foundation models.
-
🌱 We host workshops and seminars on safe reinforcement learning. Researchers and students interested in safe RL are welcome to join! Recordings are available on the Safe RL YouTube Channel. For more information, visit the Safe RL Seminar Homepage or the Safe RL Workshop Homepage.