{"total":22,"rows":[{"id":"2603.04356","title":"RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots","created":"2026-03-04","cited_by_count":79,"area":null},{"id":"2607.04434","title":"RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies","created":"2026-07-05","cited_by_count":40,"area":null},{"id":"2512.16881","title":"PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies","created":"2025-12-18","cited_by_count":33,"area":null},{"id":"2511.04665","title":"Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions","created":"2025-11-06","cited_by_count":30,"area":null},{"id":"2604.09860","title":"RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies","created":"2026-04-10","cited_by_count":24,"area":null},{"id":"2602.16863","title":"SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation","created":"2026-02-18","cited_by_count":15,"area":null},{"id":"2509.18282","title":"PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies","created":"2025-09-22","cited_by_count":12,"area":null},{"id":"2509.00117","title":"Embodied AI: Emerging Risks and Opportunities for Policy Action","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2511.17411","title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2606.11901","title":"DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2604.05226","title":"RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2606.16826","title":"ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2604.26689","title":"Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probes","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.29898","title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31494","title":"Robustness of Robotic Manipulation: Foundations and Frontiers","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.26121","title":"Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.06898","title":"How Should I Pick a Foundation Model for My Robot? In Favor of a Community Evaluation Framework for Social Robots","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.16556","title":"DeepInsight II: One Trace from Benchmark to Robot","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.09250","title":"No Free Checker: A Survey of Verifiers for Robot Policies","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.19413","title":"From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.22299","title":"When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.08125","title":"Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}