{"total":26,"rows":[{"id":"2402.08191","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","created":"2024-02-13","cited_by_count":133,"area":null},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125,"area":null},{"id":"2304.04321","title":"ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes","created":"2023-04-09","cited_by_count":69,"area":null},{"id":"2309.15596","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","created":"2023-09-27","cited_by_count":56,"area":null},{"id":"2410.01345","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2504.01786","title":"BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing","created":"2025-04-02","cited_by_count":31,"area":null},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2310.12020","title":"LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation","created":"2023-10-18","cited_by_count":17,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2308.03620","title":"Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods","created":"2023-08-07","cited_by_count":15,"area":null},{"id":"2403.08355","title":"NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2308.00937","title":"LEMMA: Learning Language-Conditioned Multi-Robot Manipulation","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2402.08369","title":"One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2406.13636","title":"Contrast Sets for Evaluating Language-Guided Robot Policies","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2407.06951","title":"RoboCAS: A Benchmark for Robotic Manipulation in Complex Object Arrangement Scenarios","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2605.08747","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","created":"2026-05-09","cited_by_count":7,"area":null},{"id":"2410.06678","title":"M3Bench: Benchmarking Whole-body Motion Generation for Mobile Manipulation in 3D Scenes","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2404.15194","title":"Closed Loop Interactive Embodied Reasoning for Robot Manipulation","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2212.05211","title":"OpenD: A Benchmark for Language-Driven Door and Drawer Opening","created":"2022-12-10","cited_by_count":3,"area":null},{"id":"2512.18028","title":"Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2303.02871","title":"Naming Objects for Vision-and-Language Manipulation","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2511.20330","title":"ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulation","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2609.19554","title":"VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2607.22119","title":"One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.39599","title":"Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}