{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129},{"id":"2601.14352","title":"RoboBrain 2.5: Depth in Sight, Time in Mind","created":"2026-01-20","cited_by_count":39},{"id":"2409.17126","title":"Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset","created":"2024-09-25","cited_by_count":15},{"id":"2210.17217","title":"AutoBag: Learning to Open Plastic Bags and Insert Objects","created":"2022-10-31","cited_by_count":14},{"id":"2205.02671","title":"What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-05-05","cited_by_count":10},{"id":"2509.01746","title":"Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference","created":"2025-09-01","cited_by_count":8},{"id":"2303.16898","title":"Bagging by Learning to Singulate Layers Using Interactive Perception","created":"2023-03-29","cited_by_count":7},{"id":"2210.07420","title":"Learning to Efficiently Plan Robust Frictional Multi-Object Grasps","created":"2022-10-13","cited_by_count":5},{"id":"2303.08975","title":"HANDLOOM: Learned Tracing of One-Dimensional Objects for Inspection and Manipulation","created":"2023-03-15","cited_by_count":5},{"id":"2106.08897","title":"Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data","created":"2021-06-16","cited_by_count":4},{"id":"2408.14769","title":"Points2Plans: From Point Clouds to Long-Horizon Plans with Composable Relational Dynamics","created":"2024-08-27","cited_by_count":4},{"id":"2505.15712","title":"TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games","created":"2025-05-21","cited_by_count":4},{"id":"2004.10251","title":"Industrial Robot Grasping with Deep Learning using a Programmable Logic Controller (PLC)","created":"2020-04-21","cited_by_count":2},{"id":"2309.16778","title":"Coupled Active Perception and Manipulation Planning for a Mobile Manipulator in Precision Agriculture Applications","created":"2023-09-28","cited_by_count":2},{"id":"2508.00354","title":"Omni-Scan: Creating Visually-Accurate Digital Twin Object Models Using a Bimanual Robot with Handover and Gaussian Splat Merging","created":"2025-08-01","cited_by_count":2},{"id":"2208.10472","title":"Automated Pruning of Polyculture Plants","created":"2022-08-22","cited_by_count":1},{"id":"2306.17162","title":"Can Machines Garden? Systematically Comparing the AlphaGarden vs. Professional Horticulturalists","created":"2023-06-29","cited_by_count":1},{"id":"2310.16951","title":"The Teenager's Problem: Efficient Garment Decluttering as Probabilistic Set Cover","created":"2023-10-25","cited_by_count":1},{"id":"2407.04929","title":"Toward Precise Robotic Weed Flaming Using a Mobile Manipulator with a Flamethrower","created":"2024-07-06","cited_by_count":1},{"id":"2408.12593","title":"Automating Deformable Gasket Assembly","created":"2024-08-22","cited_by_count":1},{"id":"2411.00221","title":"BOMP: Bin-Optimized Motion Planning","created":"2024-10-31","cited_by_count":1},{"id":"2504.03938","title":"Energy Efficient Planning for Repetitive Heterogeneous Tasks in Precision Agriculture","created":"2025-04-04","cited_by_count":1},{"id":"2510.17783","title":"Botany-Bot: Digital Twin Monitoring of Occluded and Underleaf Plant Structures with Gaussian Splats","created":"2025-10-20","cited_by_count":1},{"id":"2510.25768","title":"STITCH 2.0: Extending Augmented Suturing with EKF Needle Estimation and Thread Management","created":"2025-10-29","cited_by_count":1}],"next_cursor":null}