{"total":5,"rows":[{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2506.14186","title":"Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2411.02189","title":"DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2506.08756","title":"Bayesian Inverse Physics for Neuro-Symbolic Robot Learning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2609.33169","title":"When Does Backpropagating Through Policy Memory Matter? Physical Credit, Optimizer Updates, and Observability","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}