{"total":7,"rows":[{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216,"area":null},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16,"area":null},{"id":"2309.10657","title":"Learning Adaptive Safety for Multi-Agent Systems","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2302.01399","title":"Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2306.17598","title":"Navigation of micro-robot swarms for targeted delivery using reinforcement learning","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2509.19972","title":"An effective control of large systems of active particles: An application to evacuation problem","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2610.10367","title":"Temporally Interpretable Differentiable Decision Trees","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}